From 46c8561173fc6296993cc8d9ca1661742b4572f2 Mon Sep 17 00:00:00 2001 From: Alex Clarke Date: Wed, 2 Sep 2026 13:38:56 -0600 Subject: [PATCH] feat: generate the model catalog from live API data Add a hidden --generate-models flag that rebuilds models.yaml from models.dev and OpenRouter merged with the hand-owned quirks overlay, regenerate the committed catalog with it (393 -> 1090 models), and retire the Python updater. GitHub becomes fully quirks-owned since upstream only tracks Copilot ids, legacy ids upstream dropped are preserved as hand-owned quirks entries, and non-chat model families (image/tts/audio/realtime) are excluded from generation. --- models.yaml | 12326 ++++++++++++++++++++++++++++--------- quirks.yaml | 592 ++ scripts/requirements.txt | 2 - scripts/update_models.py | 255 - src/cli/mod.rs | 25 +- src/client/catalog.rs | 125 +- src/client/model.rs | 2 +- src/main.rs | 7 +- 8 files changed, 10276 insertions(+), 3058 deletions(-) delete mode 100644 scripts/requirements.txt delete mode 100644 scripts/update_models.py diff --git a/models.yaml b/models.yaml index 2502e8c..a368855 100644 --- a/models.yaml +++ b/models.yaml @@ -1,2850 +1,9590 @@ -# Links: -# - https://platform.openai.com/docs/models -# - https://platform.openai.com/docs/api-reference/chat +# GENERATED by 'coyote --generate-models' — DO NOT hand-edit model data. +# Hand-owned behavior lives in quirks.yaml; this file is the embedded offline fallback. - provider: openai models: - - name: gpt-5.6-sol - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 5 - output_price: 30 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh, max] - default_reasoning_effort: medium - - name: gpt-5.6-terra - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 5 - output_price: 30 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh, max] - default_reasoning_effort: medium - - name: gpt-5.6-luna - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 5 - output_price: 30 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh, max] - default_reasoning_effort: medium - - name: gpt-5.5 - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 5 - output_price: 30 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: medium - - name: gpt-5.5-pro - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 30 - output_price: 180 - supports_vision: true - supports_function_calling: true - reasoning_levels: [medium, high, xhigh] - default_reasoning_effort: high - - name: gpt-5.4 - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 2.5 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: none - - name: gpt-5.4-pro - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 30 - output_price: 180 - supports_vision: true - supports_function_calling: true - reasoning_levels: [medium, high, xhigh] - default_reasoning_effort: medium - - name: gpt-5.4-mini - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 0.75 - output_price: 4.5 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: none - - name: gpt-5.4-nano - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 0.2 - output_price: 1.25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: none - - name: gpt-5.3-codex - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.75 - output_price: 14 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh] - default_reasoning_effort: medium - - name: chat-latest - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 5 - output_price: 30 - supports_vision: true - supports_function_calling: true - - name: gpt-5.2 - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.75 - output_price: 14 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: none - - name: gpt-5.2-pro - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 21 - output_price: 168 - supports_vision: true - supports_function_calling: true - reasoning_levels: [medium, high, xhigh] - default_reasoning_effort: medium - - name: gpt-5.1 - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high] - default_reasoning_effort: none - - name: gpt-5.1-chat-latest - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high] - default_reasoning_effort: none - - name: gpt-5 - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: medium - - name: gpt-5-chat-latest - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: medium - - name: gpt-5-mini - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 0.25 - output_price: 2 - supports_vision: true - supports_function_calling: true - - name: gpt-5-nano - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 0.05 - output_price: 0.4 - supports_vision: true - supports_function_calling: true - - name: gpt-4.1 - max_input_tokens: 1047576 - max_output_tokens: 32768 - input_price: 2 - output_price: 8 - supports_vision: true - supports_function_calling: true - - name: gpt-4.1-mini - max_input_tokens: 1047576 - max_output_tokens: 32768 - input_price: 0.4 - output_price: 1.6 - supports_vision: true - supports_function_calling: true - - name: gpt-4.1-nano - max_input_tokens: 1047576 - max_output_tokens: 32768 - input_price: 0.1 - output_price: 0.4 - supports_vision: true - supports_function_calling: true - - name: gpt-4o - max_input_tokens: 128000 - max_output_tokens: 16384 - input_price: 2.5 - output_price: 10 - supports_vision: true - supports_function_calling: true - - name: gpt-4o-mini - max_input_tokens: 128000 - max_output_tokens: 16384 - input_price: 0.15 - output_price: 0.6 - supports_vision: true - supports_function_calling: true - - name: o4-mini - max_output_tokens: 100000 - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - reasoning_levels: [low, medium, high] - default_reasoning_effort: medium - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: o4-mini-high - max_output_tokens: 100000 - real_name: o4-mini - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - - name: o3 - max_output_tokens: 100000 - max_input_tokens: 200000 - input_price: 2 - output_price: 8 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: o3-high - real_name: o3 - max_input_tokens: 200000 - input_price: 2 - output_price: 8 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - - name: o3-mini - max_output_tokens: 100000 - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: o3-mini-high - max_output_tokens: 100000 - real_name: o3-mini - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - - name: gpt-4-turbo - max_input_tokens: 128000 - max_output_tokens: 4096 - input_price: 10 - output_price: 30 - supports_vision: true - supports_function_calling: true - - name: gpt-3.5-turbo - max_input_tokens: 16385 - max_output_tokens: 4096 - input_price: 0.5 - output_price: 1.5 - supports_function_calling: true - - name: text-embedding-3-large - type: embedding - input_price: 0.13 - max_tokens_per_chunk: 8191 - default_chunk_size: 2000 - max_batch_size: 100 - - name: text-embedding-3-small - type: embedding - input_price: 0.02 - max_tokens_per_chunk: 8191 - default_chunk_size: 2000 - max_batch_size: 100 - -# Links: -# - https://ai.google.dev/models/gemini -# - https://ai.google.dev/pricing -# - https://ai.google.dev/api/rest/v1beta/models/streamGenerateContent + - name: text-embedding-3-large + type: embedding + input_price: 0.13 + max_tokens_per_chunk: 8191 + default_chunk_size: 2000 + max_batch_size: 100 + - name: text-embedding-3-small + type: embedding + input_price: 0.02 + max_tokens_per_chunk: 8191 + default_chunk_size: 2000 + max_batch_size: 100 + - name: o4-mini-high + type: chat + real_name: o4-mini + max_input_tokens: 200000 + input_price: 1.1 + output_price: 4.4 + patch: + body: + reasoning_effort: high + max_tokens: null + temperature: null + top_p: null + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + system_prompt_prefix: Formatting re-enabled + - name: o3-high + type: chat + real_name: o3 + max_input_tokens: 200000 + input_price: 2.0 + output_price: 8.0 + patch: + body: + reasoning_effort: high + max_tokens: null + temperature: null + top_p: null + supports_vision: true + supports_function_calling: true + system_prompt_prefix: Formatting re-enabled + - name: o3-mini-high + type: chat + real_name: o3-mini + max_input_tokens: 200000 + input_price: 1.1 + output_price: 4.4 + patch: + body: + reasoning_effort: high + max_tokens: null + temperature: null + top_p: null + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + system_prompt_prefix: Formatting re-enabled + - name: chat-latest + type: chat + max_input_tokens: 400000 + input_price: 5.0 + output_price: 30.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: gpt-5.1-chat-latest + type: chat + max_input_tokens: 400000 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + default_reasoning_effort: none + - name: gpt-5-chat-latest + type: chat + max_input_tokens: 400000 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: medium + - name: gpt-5.6 + type: chat + max_input_tokens: 1050000 + input_price: 4.0 + output_price: 20.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + - name: gpt-5.6-luna + type: chat + max_input_tokens: 1050000 + input_price: 0.2 + output_price: 1.2 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: gpt-5.6-sol + type: chat + max_input_tokens: 1050000 + input_price: 4.0 + output_price: 20.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: gpt-5.6-terra + type: chat + max_input_tokens: 1050000 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: gpt-5.5 + type: chat + max_input_tokens: 1050000 + input_price: 5.0 + output_price: 30.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: medium + - name: gpt-5.5-pro + type: chat + max_input_tokens: 1050000 + input_price: 30.0 + output_price: 180.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - medium + - high + - xhigh + default_reasoning_effort: high + - name: gpt-5.4-mini + type: chat + max_input_tokens: 400000 + input_price: 0.75 + output_price: 4.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: none + - name: gpt-5.4-nano + type: chat + max_input_tokens: 400000 + input_price: 0.2 + output_price: 1.25 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: none + - name: gpt-5.4 + type: chat + max_input_tokens: 1050000 + input_price: 2.5 + output_price: 15.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: none + - name: gpt-5.4-pro + type: chat + max_input_tokens: 1050000 + input_price: 30.0 + output_price: 180.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - medium + - high + - xhigh + default_reasoning_effort: medium + - name: gpt-5.3-chat-latest + type: chat + max_input_tokens: 128000 + input_price: 1.75 + output_price: 14.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: gpt-5.3-codex + type: chat + max_input_tokens: 400000 + input_price: 1.75 + output_price: 14.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: medium + - name: gpt-5.3-codex-spark + type: chat + max_input_tokens: 128000 + input_price: 1.75 + output_price: 14.0 + max_output_tokens: 32000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - name: gpt-5.2 + type: chat + max_input_tokens: 400000 + input_price: 1.75 + output_price: 14.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: none + - name: gpt-5.2-chat-latest + type: chat + max_input_tokens: 128000 + input_price: 1.75 + output_price: 14.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - medium + - name: gpt-5.2-pro + type: chat + max_input_tokens: 400000 + input_price: 21.0 + output_price: 168.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - medium + - high + - xhigh + default_reasoning_effort: medium + - name: gpt-5.1 + type: chat + max_input_tokens: 400000 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + default_reasoning_effort: none + - name: gpt-5-pro + type: chat + max_input_tokens: 400000 + input_price: 15.0 + output_price: 120.0 + max_output_tokens: 272000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - high + - name: gpt-5 + type: chat + max_input_tokens: 400000 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: medium + - name: gpt-5-mini + type: chat + max_input_tokens: 400000 + input_price: 0.25 + output_price: 2.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: gpt-5-nano + type: chat + max_input_tokens: 400000 + input_price: 0.05 + output_price: 0.4 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: o3-pro + type: chat + max_input_tokens: 200000 + input_price: 20.0 + output_price: 80.0 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: o3 + type: chat + max_input_tokens: 200000 + input_price: 2.0 + output_price: 8.0 + patch: + body: + max_tokens: null + temperature: null + top_p: null + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + system_prompt_prefix: Formatting re-enabled + - name: o4-mini + type: chat + max_input_tokens: 200000 + input_price: 1.1 + output_price: 4.4 + patch: + body: + max_tokens: null + temperature: null + top_p: null + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + default_reasoning_effort: medium + system_prompt_prefix: Formatting re-enabled + - name: gpt-4.1 + type: chat + max_input_tokens: 1047576 + input_price: 2.0 + output_price: 8.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: gpt-4.1-mini + type: chat + max_input_tokens: 1047576 + input_price: 0.4 + output_price: 1.6 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: gpt-4.1-nano + type: chat + max_input_tokens: 1047576 + input_price: 0.1 + output_price: 0.4 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: o1-pro + type: chat + max_input_tokens: 200000 + input_price: 150.0 + output_price: 600.0 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: o3-mini + type: chat + max_input_tokens: 200000 + input_price: 1.1 + output_price: 4.4 + patch: + body: + max_tokens: null + temperature: null + top_p: null + max_output_tokens: 100000 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + system_prompt_prefix: Formatting re-enabled + - name: o1 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 60.0 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: gpt-4o-2024-11-20 + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: gpt-4o-2024-08-06 + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: gpt-4o-mini + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: gpt-4o + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: gpt-4o-2024-05-13 + type: chat + max_input_tokens: 128000 + input_price: 5.0 + output_price: 15.0 + max_output_tokens: 4096 + supports_vision: true + supports_function_calling: true + - name: gpt-4 + type: chat + max_input_tokens: 8192 + input_price: 30.0 + output_price: 60.0 + max_output_tokens: 8192 + supports_function_calling: true + - name: gpt-4-turbo + type: chat + max_input_tokens: 128000 + input_price: 10.0 + output_price: 30.0 + max_output_tokens: 4096 + supports_vision: true + supports_function_calling: true + - name: gpt-3.5-turbo + type: chat + max_input_tokens: 16385 + input_price: 0.5 + output_price: 1.5 + max_output_tokens: 4096 + supports_function_calling: true - provider: gemini models: - - name: gemini-3.6-flash - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 1.5 - output_price: 7.5 - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_level: medium - - name: gemini-3.5-flash - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: medium - - name: gemini-3-flash-preview - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: high - - name: gemini-3.1-flash-lite - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: minimal - - name: gemini-3.1-pro-preview - max_input_tokens: 1048576 - max_output_tokens: 65535 - input_price: 0.3 - output_price: 2.5 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high] - default_reasoning_effort: high - - name: gemini-2.5-flash - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0 - output_price: 0 - supports_vision: true - supports_function_calling: true - - name: gemini-2.5-pro - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0 - output_price: 0 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high] - default_reasoning_effort: high - - name: gemini-2.5-flash-lite - max_input_tokens: 1000000 - max_output_tokens: 64000 - input_price: 0 - output_price: 0 - supports_vision: true - supports_function_calling: true - - name: gemini-3-pro-preview - max_input_tokens: 1048576 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, high] - default_reasoning_level: high - - name: gemini-3-flash-preview - max_input_tokens: 1048576 - supports_vision: true - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_level: high - - name: gemma-3-27b-it - max_input_tokens: 131072 - max_output_tokens: 8192 - input_price: 0 - output_price: 0 - - name: text-embedding-004 - type: embedding - input_price: 0 - max_tokens_per_chunk: 2048 - default_chunk_size: 1500 - max_batch_size: 100 - -# Links: -# - https://docs.anthropic.com/en/docs/about-claude/models/all-models -# - https://docs.anthropic.com/en/api/messages + - name: text-embedding-004 + type: embedding + input_price: 0.0 + max_tokens_per_chunk: 2048 + default_chunk_size: 1500 + max_batch_size: 100 + - name: gemini-3-pro-preview + type: chat + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + default_reasoning_effort: high + - name: gemma-3-27b-it + type: chat + max_input_tokens: 131072 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 8192 + - name: gemini-3.8-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: gemini-3.7-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: gemini-flash-latest + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: gemini-3.5-flash-lite + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 2.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: gemini-3.6-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: medium + - name: gemini-flash-lite-latest + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 2.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: gemini-3.1-flash-lite-image + type: chat + max_input_tokens: 65536 + input_price: 0.25 + output_price: 30.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - high + - name: gemini-omni-flash-preview + type: chat + max_input_tokens: 131072 + input_price: 1.5 + output_price: 17.5 + max_output_tokens: 65536 + supports_vision: true + - name: gemini-3.5-live-translate-preview + type: chat + max_input_tokens: 16384 + input_price: 3.5 + output_price: 21.0 + max_output_tokens: 32768 + - name: gemini-3-pro-image + type: chat + max_input_tokens: 131072 + input_price: 2.0 + output_price: 120.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + - name: gemini-3.1-flash-image + type: chat + max_input_tokens: 65536 + input_price: 0.5 + output_price: 60.0 + max_output_tokens: 65536 + supports_vision: true + reasoning_levels: + - minimal + - high + - name: gemini-3.5-flash + type: chat + max_input_tokens: 1048576 + input_price: 1.5 + output_price: 9.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: medium + - name: gemini-3.1-flash-lite + type: chat + max_input_tokens: 1048576 + input_price: 0.25 + output_price: 1.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: minimal + - name: deep-research-max-preview-04-2026 + type: chat + max_input_tokens: 131072 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: deep-research-preview-04-2026 + type: chat + max_input_tokens: 131072 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: gemma-4-26b-a4b-it + type: chat + max_input_tokens: 262144 + input_price: 0.07 + output_price: 0.34 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: gemma-4-31b-it + type: chat + max_input_tokens: 262144 + input_price: 0.09 + output_price: 0.34 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: gemini-3.1-flash-live-preview + type: chat + max_input_tokens: 131072 + input_price: 0.75 + output_price: 4.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: lyria-3-clip-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 65536 + supports_vision: true + - name: lyria-3-pro-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 65536 + supports_vision: true + - name: gemini-3.1-flash-lite-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.25 + output_price: 1.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: gemini-3.1-pro-preview + type: chat + max_input_tokens: 1048576 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + default_reasoning_effort: high + - name: gemini-3.1-pro-preview-customtools + type: chat + max_input_tokens: 1048576 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: gemini-3-flash-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: high + - name: gemini-2.5-computer-use-preview-10-2025 + type: chat + max_input_tokens: 131072 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: gemini-2.5-flash-image + type: chat + max_input_tokens: 32768 + input_price: 0.3 + output_price: 30.0 + max_output_tokens: 32768 + supports_vision: true + - name: gemini-2.5-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 2.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: gemini-2.5-flash-lite + type: chat + max_input_tokens: 1048576 + input_price: 0.1 + output_price: 0.4 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: gemini-2.5-pro + type: chat + max_input_tokens: 1048576 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + default_reasoning_effort: high - provider: claude models: - - name: claude-opus-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-fable-5-1 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 10 - output_price: 50 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-fable-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 10 - output_price: 50 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-opus-4-8 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-opus-4-7 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-opus-4-6 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, max] - default_reasoning_effort: high - - name: claude-opus-4-6:thinking - real_name: claude-opus-4-6 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-sonnet-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-sonnet-4-6 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, max] - default_reasoning_effort: high - - name: claude-sonnet-4-6:thinking - real_name: claude-sonnet-4-6 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-sonnet-4-5-20250929 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - - name: claude-sonnet-4-5-20250929:thinking - real_name: claude-sonnet-4-5-20250929 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-haiku-4-5-20251001 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 1 - output_price: 5 - supports_vision: true - supports_function_calling: true - - name: claude-haiku-4-5-20251001:thinking - real_name: claude-haiku-4-5-20251001 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 1 - output_price: 5 - supports_vision: true - supports_function_calling: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-opus-4-5-20251101 - type: chat - max_input_tokens: 200000 - input_price: 15.0 - output_price: 75.0 - max_output_tokens: 8192 - require_max_tokens: true - supports_vision: true - supports_function_calling: true - - name: claude-opus-4-5-20251101:thinking - type: chat - real_name: claude-opus-4-5-20251101 - max_input_tokens: 200000 - input_price: 15.0 - output_price: 75.0 - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - max_output_tokens: 24000 - require_max_tokens: true - supports_vision: true - supports_function_calling: true - - name: claude-opus-4-1-20250805 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 15 - output_price: 75 - supports_vision: true - supports_function_calling: true - - name: claude-opus-4-1-20250805:thinking - real_name: claude-opus-4-1-20250805 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 15 - output_price: 75 - supports_vision: true - supports_function_calling: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-opus-4-20250514 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 15 - output_price: 75 - supports_vision: true - supports_function_calling: true - - name: claude-opus-4-20250514:thinking - real_name: claude-opus-4-20250514 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 15 - output_price: 75 - supports_vision: true - supports_function_calling: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-sonnet-4-5-20250929 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - - name: claude-sonnet-4-5-20250929:thinking - real_name: claude-sonnet-4-5-20250929 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-haiku-4-5-20251001 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 1 - output_price: 5 - supports_vision: true - supports_function_calling: true - - name: claude-haiku-4-5-20251001:thinking - real_name: claude-haiku-4-5-20251001 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 1 - output_price: 5 - supports_vision: true - supports_function_calling: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - -# Links: -# - https://docs.mistral.ai/getting-started/models/models_overview/ -# - https://mistral.ai/pricing#api-pricing -# - https://docs.mistral.ai/api/ + - name: claude-opus-4-1-20250805 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + max_output_tokens: 8192 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-opus-4-1-20250805:thinking + type: chat + real_name: claude-opus-4-1-20250805 + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-opus-4-20250514 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + max_output_tokens: 8192 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-opus-4-20250514:thinking + type: chat + real_name: claude-opus-4-20250514 + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-fable-5-1 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-opus-5 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-sonnet-5 + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-fable-5 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-opus-4-8 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-opus-4-7 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-sonnet-4-6 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + default_reasoning_effort: high + - name: claude-sonnet-4-6:thinking + type: chat + real_name: claude-sonnet-4-6 + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + default_reasoning_effort: high + - name: claude-opus-4-6 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + default_reasoning_effort: high + - name: claude-opus-4-6:thinking + type: chat + real_name: claude-opus-4-6 + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + default_reasoning_effort: high + - name: claude-opus-4-5 + type: chat + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: claude-opus-4-5-20251101 + type: chat + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: claude-opus-4-5-20251101:thinking + type: chat + real_name: claude-opus-4-5-20251101 + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-haiku-4-5 + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-haiku-4-5-20251001 + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-haiku-4-5-20251001:thinking + type: chat + real_name: claude-haiku-4-5-20251001 + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-sonnet-4-5 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-sonnet-4-5-20250929 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-sonnet-4-5-20250929:thinking + type: chat + real_name: claude-sonnet-4-5-20250929 + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true - provider: mistral models: - - name: mistral-large-latest - max_output_tokens: 262144 - input_price: 0.5 - output_price: 1.5 - supports_function_calling: true - supports_vision: true - - name: mistral-medium-latest - max_input_tokens: 131072 - input_price: 0.4 - output_price: 2 - supports_function_calling: true - supports_vision: true - - name: mistral-small-latest - max_input_tokens: 32768 - input_price: 0.1 - output_price: 0.3 - supports_function_calling: true - supports_vision: true - - name: magistral-medium-latest - max_input_tokens: 131072 - input_price: 2 - output_price: 5 - - name: magistral-small-latest - max_input_tokens: 131072 - input_price: 0.5 - output_price: 1.5 - - name: devstral-medium-latest - max_input_tokens: 262144 - input_price: 0.4 - output_price: 2 - supports_function_calling: true - - name: devstral-small-latest - max_input_tokens: 262144 - input_price: 0.1 - output_price: 0.3 - supports_function_calling: true - - name: codestral-latest - max_input_tokens: 262144 - input_price: 0.3 - output_price: 0.9 - supports_function_calling: true - - name: ministral-14b-latest - max_input_tokens: 262144 - input_price: 0.2 - output_price: 0.2 - supports_function_calling: true - - name: mistral-embed - type: embedding - max_input_tokens: 8092 - input_price: 0.1 - max_tokens_per_chunk: 8092 - default_chunk_size: 2000 - -# Links: -# - https://docs.ai21.com/docs/jamba-foundation-models -# - https://www.ai21.com/pricing -# - https://docs.ai21.com/reference/jamba-1-6-api-ref + - name: mistral-embed + type: embedding + max_input_tokens: 8092 + input_price: 0.1 + output_price: 0.0 + max_output_tokens: 3072 + max_tokens_per_chunk: 8092 + default_chunk_size: 2000 + - name: magistral-small-latest + type: chat + max_input_tokens: 131072 + input_price: 0.5 + output_price: 1.5 + - name: devstral-small-latest + type: chat + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.3 + supports_function_calling: true + - name: ministral-14b-latest + type: chat + max_input_tokens: 262144 + input_price: 0.2 + output_price: 0.2 + supports_function_calling: true + - name: zai-glm-5-2 + type: chat + max_input_tokens: 1000000 + input_price: 1.4 + output_price: 4.4 + max_output_tokens: 131072 + supports_function_calling: true + reasoning_levels: + - high + - max + - name: mistral-medium-2604 + type: chat + max_input_tokens: 262144 + input_price: 1.5 + output_price: 7.5 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - high + - name: mistral-medium-latest + type: chat + max_input_tokens: 262144 + input_price: 1.5 + output_price: 7.5 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - high + - name: mistral-small-2603 + type: chat + max_input_tokens: 256000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 256000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - high + - name: mistral-small-latest + type: chat + max_input_tokens: 256000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 256000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - high + - name: devstral-2512 + type: chat + max_input_tokens: 262144 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 262144 + supports_function_calling: true + - name: devstral-latest + type: chat + max_input_tokens: 262144 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 262144 + supports_function_calling: true + - name: labs-devstral-small-2512 + type: chat + max_input_tokens: 256000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 256000 + supports_vision: true + supports_function_calling: true + - name: devstral-medium-latest + type: chat + max_input_tokens: 262144 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 262144 + supports_function_calling: true + - name: mistral-medium-2508 + type: chat + max_input_tokens: 262144 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: devstral-medium-2507 + type: chat + max_input_tokens: 128000 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 128000 + supports_function_calling: true + - name: devstral-small-2507 + type: chat + max_input_tokens: 128000 + input_price: 0.1 + output_price: 0.3 + max_output_tokens: 128000 + supports_function_calling: true + - name: mistral-small-2506 + type: chat + max_input_tokens: 128000 + input_price: 0.1 + output_price: 0.3 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: devstral-small-2505 + type: chat + max_input_tokens: 128000 + input_price: 0.1 + output_price: 0.3 + max_output_tokens: 128000 + supports_function_calling: true + - name: mistral-medium-2505 + type: chat + max_input_tokens: 131072 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: magistral-medium-latest + type: chat + max_input_tokens: 128000 + input_price: 2.0 + output_price: 5.0 + max_output_tokens: 16384 + supports_function_calling: true + - name: magistral-small + type: chat + max_input_tokens: 128000 + input_price: 0.5 + output_price: 1.5 + max_output_tokens: 128000 + supports_function_calling: true + - name: mistral-large-2411 + type: chat + max_input_tokens: 131072 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 16384 + supports_function_calling: true + - name: mistral-large-2512 + type: chat + max_input_tokens: 262144 + input_price: 0.5 + output_price: 1.5 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: mistral-large-latest + type: chat + max_input_tokens: 262144 + input_price: 0.5 + output_price: 1.5 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: pixtral-large-latest + type: chat + max_input_tokens: 128000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: ministral-3b-latest + type: chat + max_input_tokens: 128000 + input_price: 0.04 + output_price: 0.04 + max_output_tokens: 128000 + supports_function_calling: true + - name: ministral-8b-latest + type: chat + max_input_tokens: 128000 + input_price: 0.1 + output_price: 0.1 + max_output_tokens: 128000 + supports_function_calling: true + - name: pixtral-12b + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.15 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: mistral-nemo + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.15 + max_output_tokens: 128000 + supports_function_calling: true + - name: open-mistral-nemo + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.15 + max_output_tokens: 128000 + supports_function_calling: true + - name: codestral-latest + type: chat + max_input_tokens: 256000 + input_price: 0.3 + output_price: 0.9 + max_output_tokens: 4096 + supports_function_calling: true + - name: open-mixtral-8x22b + type: chat + max_input_tokens: 64000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 64000 + supports_function_calling: true + - name: open-mixtral-8x7b + type: chat + max_input_tokens: 32000 + input_price: 0.7 + output_price: 0.7 + max_output_tokens: 32000 + supports_function_calling: true + - name: open-mistral-7b + type: chat + max_input_tokens: 8000 + input_price: 0.25 + output_price: 0.25 + max_output_tokens: 8000 + supports_function_calling: true - provider: ai21 models: - - name: jamba-large - max_input_tokens: 256000 - input_price: 2 - output_price: 8 - supports_function_calling: true - - name: jamba-mini - max_input_tokens: 256000 - input_price: 0.2 - output_price: 0.4 - supports_function_calling: true - -# Links: -# - https://docs.cohere.com/docs/models -# - https://cohere.com/pricing -# - https://docs.cohere.com/reference/chat + - name: jamba-large + type: chat + max_input_tokens: 256000 + input_price: 2.0 + output_price: 8.0 + supports_function_calling: true + - name: jamba-mini + type: chat + max_input_tokens: 256000 + input_price: 0.2 + output_price: 0.4 + supports_function_calling: true - provider: cohere models: - - name: command-a-03-2025 - max_input_tokens: 262144 - max_output_tokens: 8192 - input_price: 2.5 - output_price: 10 - supports_function_calling: true - - name: command-a-reasoning-08-2025 - max_input_tokens: 262144 - max_output_tokens: 32768 - input_price: 2.5 - output_price: 10 - - name: command-a-vision-07-2025 - max_input_tokens: 131072 - max_output_tokens: 8192 - input_price: 2.5 - output_price: 10 - supports_vision: true - - name: command-r7b-12-2024 - max_input_tokens: 131072 - max_output_tokens: 4096 - input_price: 0.0375 - output_price: 0.15 - - name: embed-v4.0 - type: embedding - input_price: 0.12 - max_tokens_per_chunk: 2048 - default_chunk_size: 2000 - max_batch_size: 96 - - name: embed-english-v3.0 - type: embedding - input_price: 0.1 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 96 - - name: embed-multilingual-v3.0 - type: embedding - input_price: 0.1 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 96 - - name: rerank-v3.5 - type: reranker - max_input_tokens: 4096 - - name: rerank-english-v3.0 - type: reranker - max_input_tokens: 4096 - - name: rerank-multilingual-v3.0 - type: reranker - max_input_tokens: 4096 - -# Links: -# - https://docs.x.ai/docs/models -# - https://docs.x.ai/docs/api-reference#chat-completions + - name: embed-v4.0 + type: embedding + input_price: 0.12 + max_tokens_per_chunk: 2048 + default_chunk_size: 2000 + max_batch_size: 96 + - name: embed-english-v3.0 + type: embedding + input_price: 0.1 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 96 + - name: embed-multilingual-v3.0 + type: embedding + input_price: 0.1 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 96 + - name: rerank-v3.5 + type: reranker + max_input_tokens: 4096 + - name: rerank-english-v3.0 + type: reranker + max_input_tokens: 4096 + - name: rerank-multilingual-v3.0 + type: reranker + max_input_tokens: 4096 + - name: north-mini-code-1-0 + type: chat + max_input_tokens: 256000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 64000 + supports_function_calling: true + reasoning_levels: + - none + - high + - name: command-a-plus-05-2026 + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: command-a-translate-08-2025 + type: chat + max_input_tokens: 8000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 8000 + supports_function_calling: true + - name: command-a-reasoning-08-2025 + type: chat + max_input_tokens: 256000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 32000 + supports_function_calling: true + - name: command-a-vision-07-2025 + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 8000 + supports_vision: true + - name: command-a-03-2025 + type: chat + max_input_tokens: 256000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 8000 + supports_function_calling: true + - name: c4ai-aya-vision-32b + type: chat + max_input_tokens: 16000 + max_output_tokens: 4000 + supports_vision: true + - name: c4ai-aya-vision-8b + type: chat + max_input_tokens: 16000 + max_output_tokens: 4000 + supports_vision: true + - name: command-r7b-arabic-02-2025 + type: chat + max_input_tokens: 128000 + input_price: 0.0375 + output_price: 0.15 + max_output_tokens: 4000 + supports_function_calling: true + - name: command-r7b-12-2024 + type: chat + max_input_tokens: 128000 + input_price: 0.0375 + output_price: 0.15 + max_output_tokens: 4000 + supports_function_calling: true + - name: c4ai-aya-expanse-32b + type: chat + max_input_tokens: 128000 + max_output_tokens: 4000 + - name: c4ai-aya-expanse-8b + type: chat + max_input_tokens: 8000 + max_output_tokens: 4000 + - name: command-r-08-2024 + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 4000 + supports_function_calling: true + - name: command-r-plus-08-2024 + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 4000 + supports_function_calling: true - provider: xai oauth: client_id: b1a00492-073a-47ea-816f-4c329264a828 - authorize_url: https://auth.x.ai/oauth2/authorize token_url: https://auth.x.ai/oauth2/token - scopes: - - openid - - profile - - email - - offline_access - - grok-cli:access - - api:access - redirect_port: 56121 flow: pkce + client_secret: null + authorize_url: https://auth.x.ai/oauth2/authorize + redirect_uri: null + redirect_port: 56121 + device_authorization_url: null + scopes: + - openid + - profile + - email + - offline_access + - grok-cli:access + - api:access token_request_format: form_url_encoded extra_authorize_params: plan: generic referrer: coyote + extra_token_headers: {} + extra_request_headers: {} echo_pkce_in_token_exchange: true + use_pkce_in_device_flow: false + include_state_in_token_exchange: true models: - - name: grok-4.6 - input_price: 2 - output_price: 6 - max_input_tokens: 500000 - supports_function_calling: true - - name: grok-4.5 - input_price: 2 - output_price: 6 - max_input_tokens: 256000 - supports_function_calling: true - - name: grok-build-0.1 - input_price: 1 - output_price: 2 - max_input_tokens: 256000 - supports_function_calling: true - - name: grok-4.3 - input_price: 1.25 - output_price: 2.5 - max_input_tokens: 1000000 - supports_function_calling: true - - name: grok-4.20 - real_name: grok-4.20-multi-agent-0309 - input_price: 1.25 - output_price: 2.5 - max_input_tokens: 1000000 - supports_function_calling: true - - name: grok-4.20-reasoning - real_name: grok-4.20-0309-reasoning - input_price: 1.25 - output_price: 2.5 - max_input_tokens: 1000000 - supports_function_calling: true - - name: grok-4.20-non-reasoning - real_name: grok-4.20-0309-non-reasoning - input_price: 1.25 - output_price: 2.5 - max_input_tokens: 1000000 - supports_function_calling: true - - name: grok-4-1-fast-non-reasoning - max_input_tokens: 1000000 - input_price: 0.2 - output_price: 0.5 - supports_function_calling: true - - name: grok-4-1-fast-reasoning - max_input_tokens: 1000000 - input_price: 0.2 - output_price: 0.5 - supports_function_calling: true - - name: grok-code-fast-1 - max_input_tokens: 256000 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - - name: grok-3 - max_input_tokens: 131072 - input_price: 3 - output_price: 15 - supports_function_calling: true - - name: grok-3-mini - max_input_tokens: 131072 - input_price: 0.3 - output_price: 0.5 - supports_function_calling: true - -# Links: -# - https://docs.perplexity.ai/getting-started/models -# - https://docs.perplexity.ai/api-reference/chat-completions + - name: grok-4.20 + type: chat + real_name: grok-4.20-multi-agent-0309 + max_input_tokens: 1000000 + input_price: 1.25 + output_price: 2.5 + supports_function_calling: true + - name: grok-4.20-reasoning + type: chat + real_name: grok-4.20-0309-reasoning + max_input_tokens: 1000000 + input_price: 1.25 + output_price: 2.5 + supports_function_calling: true + - name: grok-4.20-non-reasoning + type: chat + real_name: grok-4.20-0309-non-reasoning + max_input_tokens: 1000000 + input_price: 1.25 + output_price: 2.5 + supports_function_calling: true + - name: grok-4-1-fast-non-reasoning + type: chat + max_input_tokens: 1000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true + - name: grok-4-1-fast-reasoning + type: chat + max_input_tokens: 1000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true + - name: grok-code-fast-1 + type: chat + max_input_tokens: 256000 + input_price: 0.2 + output_price: 1.5 + supports_function_calling: true + - name: grok-3 + type: chat + max_input_tokens: 131072 + input_price: 3.0 + output_price: 15.0 + supports_function_calling: true + - name: grok-3-mini + type: chat + max_input_tokens: 131072 + input_price: 0.3 + output_price: 0.5 + supports_function_calling: true + - name: grok-4.6 + type: chat + max_input_tokens: 500000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 500000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - name: grok-4.5 + type: chat + max_input_tokens: 500000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 500000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: grok-4.3 + type: chat + max_input_tokens: 1000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 30000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - name: grok-build-0.1 + type: chat + max_input_tokens: 256000 + input_price: 1.0 + output_price: 2.0 + max_output_tokens: 256000 + supports_vision: true + supports_function_calling: true + - name: grok-4.20-0309-non-reasoning + type: chat + max_input_tokens: 1000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 30000 + supports_vision: true + supports_function_calling: true + - name: grok-4.20-0309-reasoning + type: chat + max_input_tokens: 1000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 30000 + supports_vision: true + supports_function_calling: true + - name: grok-4.20-multi-agent-0309 + type: chat + max_input_tokens: 1000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 30000 + supports_vision: true + reasoning_levels: + - low + - medium + - high + - xhigh - provider: perplexity models: - - name: sonar-pro - max_output_tokens: 8000 - supports_vision: true - max_input_tokens: 200000 - input_price: 3 - output_price: 15 - - name: sonar - supports_vision: true - max_input_tokens: 127072 - input_price: 1 - output_price: 1 - - name: sonar-reasoning-pro - supports_vision: true - max_input_tokens: 128000 - input_price: 2 - output_price: 8 - - name: sonar-reasoning - max_input_tokens: 128000 - input_price: 1 - output_price: 5 - - name: sonar-deep-research - max_input_tokens: 128000 - input_price: 2 - output_price: 8 - -# Links: -# - https://console.groq.com/docs/models -# - https://console.groq.com/docs/api-reference#chat + - name: sonar-reasoning + type: chat + max_input_tokens: 128000 + input_price: 1.0 + output_price: 5.0 + - name: sonar-deep-research + type: chat + max_input_tokens: 128000 + input_price: 2.0 + output_price: 8.0 + max_output_tokens: 32768 + reasoning_levels: + - minimal + - low + - medium + - high + - name: sonar + type: chat + max_input_tokens: 128000 + input_price: 1.0 + output_price: 1.0 + max_output_tokens: 4096 + supports_vision: true + - name: sonar-pro + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 8192 + supports_vision: true + - name: sonar-reasoning-pro + type: chat + max_input_tokens: 128000 + input_price: 2.0 + output_price: 8.0 + max_output_tokens: 4096 + supports_vision: true + reasoning_levels: + - minimal + - low + - medium + - high - provider: groq models: - - name: openai/gpt-oss-120b - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - supports_function_calling: true - - name: openai/gpt-oss-20b - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - supports_function_calling: true - - name: meta-llama/llama-4-maverick-17b-128e-instruct - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - supports_vision: true - supports_function_calling: true - - name: meta-llama/llama-4-scout-17b-16e-instruct - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - supports_vision: true - supports_function_calling: true - - name: llama-3.3-70b-versatile - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - supports_function_calling: true - - name: moonshotai/kimi-k2-instruct-0905 - max_input_tokens: 262144 - input_price: 0 - output_price: 0 - supports_function_calling: true - - name: qwen/qwen3-32b - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - - name: groq/compound - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - - name: groq/compound-mini - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - -# Links: -# - https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models -# - https://cloud.google.com/vertex-ai/generative-ai/pricing -# - https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/gemini + - name: meta-llama/llama-4-maverick-17b-128e-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.0 + output_price: 0.0 + supports_vision: true + supports_function_calling: true + - name: meta-llama/llama-4-scout-17b-16e-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.0 + output_price: 0.0 + supports_vision: true + supports_function_calling: true + - name: moonshotai/kimi-k2-instruct-0905 + type: chat + max_input_tokens: 262144 + input_price: 0.0 + output_price: 0.0 + supports_function_calling: true + - name: qwen/qwen3-32b + type: chat + max_input_tokens: 131072 + input_price: 0.0 + output_price: 0.0 + - name: qwen/qwen3.8-27b + type: chat + max_input_tokens: 131042 + input_price: 0.8 + output_price: 4.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - default + - low + - medium + - high + - name: qwen/qwen3.6-27b + type: chat + max_input_tokens: 131072 + input_price: 0.6 + output_price: 3.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - default + - name: canopylabs/orpheus-v1-english + type: chat + max_input_tokens: 4000 + max_output_tokens: 50000 + - name: canopylabs/orpheus-arabic-saudi + type: chat + max_input_tokens: 4000 + max_output_tokens: 50000 + - name: openai/gpt-oss-safeguard-20b + type: chat + max_input_tokens: 131072 + input_price: 0.075 + output_price: 0.3 + max_output_tokens: 65536 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: groq/compound + type: chat + max_input_tokens: 131072 + max_output_tokens: 8192 + - name: groq/compound-mini + type: chat + max_input_tokens: 131072 + max_output_tokens: 8192 + - name: openai/gpt-oss-120b + type: chat + max_input_tokens: 131072 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 65536 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: openai/gpt-oss-20b + type: chat + max_input_tokens: 131072 + input_price: 0.075 + output_price: 0.3 + max_output_tokens: 65536 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: meta-llama/llama-prompt-guard-2-22m + type: chat + max_input_tokens: 512 + input_price: 0.03 + output_price: 0.03 + max_output_tokens: 512 + - name: meta-llama/llama-prompt-guard-2-86m + type: chat + max_input_tokens: 512 + input_price: 0.04 + output_price: 0.04 + max_output_tokens: 512 + - name: allam-2-7b + type: chat + max_input_tokens: 4096 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 4096 + - name: llama-3.3-70b-versatile + type: chat + max_input_tokens: 131072 + input_price: 0.59 + output_price: 0.79 + max_output_tokens: 32768 + supports_function_calling: true + - name: llama-3.1-8b-instant + type: chat + max_input_tokens: 131072 + input_price: 0.05 + output_price: 0.08 + max_output_tokens: 131072 + supports_function_calling: true - provider: vertexai models: - - name: gemini-3.5-flash - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: medium - - name: gemini-3-flash-preview - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: high - - name: gemini-3.1-flash-lite - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - reasoning_levels: [minimal, high] - default_reasoning_effort: minimal - - name: gemini-3.1-pro-preview - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 2 - output_price: 12 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high] - default_reasoning_effort: high - - name: gemini-2.5-flash - max_input_tokens: 1048576 - max_output_tokens: 65535 - input_price: 0.3 - output_price: 2.5 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high] - default_reasoning_effort: medium - - name: gemini-2.5-pro - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high] - default_reasoning_effort: high - - name: gemini-2.5-flash-lite - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.3 - output_price: 0.4 - supports_vision: true - supports_function_calling: true - - name: gemini-3-pro-preview - max_input_tokens: 1048576 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, high] - default_reasoning_effort: high - - name: gemini-3-flash-preview - max_input_tokens: 1048576 - supports_vision: true - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: high - - name: claude-opus-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-fable-5-1 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 10 - output_price: 50 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-fable-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 10 - output_price: 50 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-opus-4-8 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-opus-4-7 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-opus-4-6 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - - name: claude-opus-4-6:thinking - real_name: claude-opus-4-6 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-sonnet-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: claude-sonnet-4-6 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, max] - default_reasoning_effort: high - - name: claude-sonnet-4-6:thinking - real_name: claude-sonnet-4-6 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-opus-4-5@20251101 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - - name: claude-opus-4-5@20251101:thinking - real_name: claude-opus-4-5@20251101 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-sonnet-4-5@20250929 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - - name: claude-sonnet-4-5@20250929:thinking - real_name: claude-sonnet-4-5@20250929 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-haiku-4-5@20251001 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 1 - output_price: 5 - supports_vision: true - supports_function_calling: true - - name: claude-haiku-4-5@20251001:thinking - real_name: claude-haiku-4-5@20251001 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 1 - output_price: 5 - supports_vision: true - patch: - body: - temperature: null - top_p: null - thinking: - type: enabled - budget_tokens: 16000 - - name: claude-3-5-haiku@20241022 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 0.8 - output_price: 4 - supports_vision: true - supports_function_calling: true - - name: mistral-small-2503 - max_input_tokens: 32000 - input_price: 0.1 - output_price: 0.3 - supports_function_calling: true - - name: codestral-2501 - max_input_tokens: 256000 - input_price: 0.3 - output_price: 0.9 - supports_function_calling: true - - name: text-embedding-005 - type: embedding - max_input_tokens: 20000 - input_price: 0.025 - max_tokens_per_chunk: 2048 - default_chunk_size: 1500 - max_batch_size: 5 - - name: text-multilingual-embedding-002 - type: embedding - max_input_tokens: 20000 - input_price: 0.2 - max_tokens_per_chunk: 2048 - default_chunk_size: 1500 - max_batch_size: 5 - -# Links: -# - https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns -# - https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-supported-models-features.html -# - https://aws.amazon.com/bedrock/pricing/ -# - https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-call.html + - name: text-embedding-005 + type: embedding + max_input_tokens: 20000 + input_price: 0.025 + max_tokens_per_chunk: 2048 + default_chunk_size: 1500 + max_batch_size: 5 + - name: text-multilingual-embedding-002 + type: embedding + max_input_tokens: 20000 + input_price: 0.2 + max_tokens_per_chunk: 2048 + default_chunk_size: 1500 + max_batch_size: 5 + - name: gemini-3-pro-preview + type: chat + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + default_reasoning_effort: high + - name: claude-opus-5 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-fable-5-1 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-fable-5 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-opus-4-8 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-opus-4-7 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-opus-4-6 + type: chat + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 8192 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-opus-4-6:thinking + type: chat + real_name: claude-opus-4-6 + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + - name: claude-sonnet-5 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-sonnet-4-6 + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 8192 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + default_reasoning_effort: high + - name: claude-sonnet-4-6:thinking + type: chat + real_name: claude-sonnet-4-6 + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + default_reasoning_effort: high + - name: claude-3-5-haiku@20241022 + type: chat + max_input_tokens: 200000 + input_price: 0.8 + output_price: 4.0 + max_output_tokens: 8192 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: mistral-small-2503 + type: chat + max_input_tokens: 32000 + input_price: 0.1 + output_price: 0.3 + supports_function_calling: true + - name: codestral-2501 + type: chat + max_input_tokens: 256000 + input_price: 0.3 + output_price: 0.9 + supports_function_calling: true + - name: gemini-3.8-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: claude-fable-5-1@default + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: gemini-3.7-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: gemini-flash-latest + type: chat + max_input_tokens: 1048576 + input_price: 1.5 + output_price: 9.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: claude-opus-5@default + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: gemini-3.5-flash-lite + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 2.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: gemini-3.6-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: gemini-flash-lite-latest + type: chat + max_input_tokens: 1048576 + input_price: 0.25 + output_price: 1.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: claude-sonnet-5@default + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: claude-fable-5@default + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: claude-opus-4-8@default + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: gemini-3-pro-image + type: chat + max_input_tokens: 65536 + input_price: 2.0 + output_price: 120.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: gemini-3.1-flash-image + type: chat + max_input_tokens: 131072 + input_price: 0.5 + output_price: 60.0 + max_output_tokens: 32768 + supports_vision: true + reasoning_levels: + - minimal + - high + - name: gemini-3.5-flash + type: chat + max_input_tokens: 1048576 + input_price: 1.5 + output_price: 9.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: medium + - name: gemini-3.1-flash-lite + type: chat + max_input_tokens: 1048576 + input_price: 0.25 + output_price: 1.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: minimal + - name: claude-opus-4-7@default + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: gemini-3.1-flash-lite-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.25 + output_price: 1.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + - name: gemini-3.1-pro-preview + type: chat + max_input_tokens: 1048576 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + default_reasoning_effort: high + - name: gemini-3.1-pro-preview-customtools + type: chat + max_input_tokens: 1048576 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: claude-sonnet-4-6@default + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: zai-org/glm-5-maas + type: chat + max_input_tokens: 202752 + input_price: 1.0 + output_price: 3.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: claude-opus-4-6@default + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: zai-org/glm-4.7-maas + type: chat + max_input_tokens: 200000 + input_price: 0.6 + output_price: 2.2 + max_output_tokens: 128000 + supports_function_calling: true + - name: deepseek-ai/deepseek-v3.2-maas + type: chat + max_input_tokens: 163840 + input_price: 0.56 + output_price: 1.68 + max_output_tokens: 65536 + supports_function_calling: true + - name: gemini-3-flash-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: high + - name: moonshotai/kimi-k2-thinking-maas + type: chat + max_input_tokens: 262144 + input_price: 0.6 + output_price: 2.5 + max_output_tokens: 262144 + supports_function_calling: true + - name: claude-opus-4-5@20251101 + type: chat + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: claude-opus-4-5@20251101:thinking + type: chat + real_name: claude-opus-4-5@20251101 + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + - name: claude-haiku-4-5@20251001 + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-haiku-4-5@20251001:thinking + type: chat + real_name: claude-haiku-4-5@20251001 + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + - name: claude-sonnet-4-5@20250929 + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-sonnet-4-5@20250929:thinking + type: chat + real_name: claude-sonnet-4-5@20250929 + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + patch: + body: + temperature: null + top_p: null + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + - name: deepseek-ai/deepseek-v3.1-maas + type: chat + max_input_tokens: 163840 + input_price: 0.6 + output_price: 1.7 + max_output_tokens: 32768 + supports_function_calling: true + - name: gemini-2.5-flash-image + type: chat + max_input_tokens: 32768 + input_price: 0.3 + output_price: 30.0 + max_output_tokens: 32768 + supports_vision: true + - name: qwen/qwen3-235b-a22b-instruct-2507-maas + type: chat + max_input_tokens: 262144 + input_price: 0.22 + output_price: 0.88 + max_output_tokens: 16384 + supports_function_calling: true + - name: claude-opus-4-1@20250805 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + max_output_tokens: 32000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: openai/gpt-oss-120b-maas + type: chat + max_input_tokens: 131072 + input_price: 0.09 + output_price: 0.36 + max_output_tokens: 32768 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: openai/gpt-oss-20b-maas + type: chat + max_input_tokens: 131072 + input_price: 0.07 + output_price: 0.25 + max_output_tokens: 32768 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: gemini-2.5-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 2.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + default_reasoning_effort: medium + - name: gemini-2.5-flash-lite + type: chat + max_input_tokens: 1048576 + input_price: 0.1 + output_price: 0.4 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: gemini-2.5-pro + type: chat + max_input_tokens: 1048576 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + default_reasoning_effort: high + - name: claude-opus-4@20250514 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + max_output_tokens: 32000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: claude-sonnet-4@20250514 + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: meta/llama-3.3-70b-instruct-maas + type: chat + max_input_tokens: 128000 + input_price: 0.72 + output_price: 0.72 + max_output_tokens: 8192 + supports_function_calling: true + - name: meta/llama-4-maverick-17b-128e-instruct-maas + type: chat + max_input_tokens: 524288 + input_price: 0.35 + output_price: 1.15 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true - provider: bedrock models: - - name: us.anthropic.claude-opus-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: us.anthropic.claude-fable-5-1 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 10 - output_price: 50 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: us.anthropic.claude-fable-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 10 - output_price: 50 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: us.anthropic.claude-opus-4-8 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: us.anthropic.claude-opus-4-7 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: us.anthropic.claude-opus-4-6-v1 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, max] - default_reasoning_effort: high - - name: us.anthropic.claude-opus-4-6-v1:thinking - real_name: us.anthropic.claude-opus-4-6-v1 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - patch: - body: - inferenceConfig: - temperature: null - topP: null - additionalModelRequestFields: - thinking: - type: enabled - budget_tokens: 16000 - - name: us.anthropic.claude-sonnet-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: us.anthropic.claude-sonnet-4-6 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, max] - default_reasoning_effort: high - - name: us.anthropic.claude-sonnet-4-6:thinking - real_name: us.anthropic.claude-sonnet-4-6 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - patch: - body: - inferenceConfig: - temperature: null - topP: null - additionalModelRequestFields: - thinking: - type: enabled - budget_tokens: 16000 - - name: us.anthropic.claude-opus-4-5-20251101-v1:0 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - - name: us.anthropic.claude-opus-4-5-20251101-v1:0:thinking - real_name: us.anthropic.claude-opus-4-5-20251101-v1:0 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - patch: - body: - inferenceConfig: - temperature: null - topP: null - additionalModelRequestFields: - thinking: - type: enabled - budget_tokens: 16000 - - name: us.anthropic.claude-sonnet-4-5-20250929-v1:0 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - - name: us.anthropic.claude-sonnet-4-5-20250929-v1:0:thinking - real_name: us.anthropic.claude-sonnet-4-5-20250929-v1:0 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - patch: - body: - inferenceConfig: - temperature: null - topP: null - additionalModelRequestFields: - thinking: - type: enabled - budget_tokens: 16000 - - name: us.anthropic.claude-haiku-4-5-20251001-v1:0 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 1 - output_price: 5 - supports_vision: true - supports_function_calling: true - - name: us.anthropic.claude-haiku-4-5-20251001-v1:0:thinking - real_name: us.anthropic.claude-haiku-4-5-20251001-v1:0 - max_input_tokens: 200000 - max_output_tokens: 24000 - require_max_tokens: true - input_price: 1 - output_price: 5 - supports_vision: true - patch: - body: - inferenceConfig: - temperature: null - topP: null - additionalModelRequestFields: - thinking: - type: enabled - budget_tokens: 16000 - - name: us.meta.llama4-maverick-17b-instruct-v1:0 - max_input_tokens: 131072 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 0.24 - output_price: 0.97 - supports_function_calling: true - supports_vision: true - - name: us.meta.llama4-scout-17b-instruct-v1:0 - max_input_tokens: 131072 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 0.17 - output_price: 0.66 - supports_function_calling: true - supports_vision: true - - name: us.meta.llama3-3-70b-instruct-v1:0 - max_input_tokens: 131072 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 0.72 - output_price: 0.72 - supports_function_calling: true - - name: us.amazon.nova-premier-v1:0 - max_input_tokens: 300000 - max_output_tokens: 5120 - input_price: 2.5 - output_price: 12.5 - - name: us.amazon.nova-pro-v1:0 - max_input_tokens: 300000 - max_output_tokens: 5120 - input_price: 0.8 - output_price: 3.2 - supports_vision: true - - name: us.amazon.nova-lite-v1:0 - max_input_tokens: 300000 - max_output_tokens: 5120 - input_price: 0.06 - output_price: 0.24 - supports_vision: true - - name: us.amazon.nova-micro-v1:0 - max_input_tokens: 128000 - max_output_tokens: 5120 - input_price: 0.035 - output_price: 0.14 - - name: cohere.embed-english-v3 - type: embedding - input_price: 0.1 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 96 - - name: cohere.embed-multilingual-v3 - type: embedding - input_price: 0.1 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 96 - - name: us.deepseek.r1-v1:0 - max_input_tokens: 128000 - input_price: 1.35 - output_price: 5.4 - -# Links: -# - https://developers.cloudflare.com/workers-ai/models/ -# - https://developers.cloudflare.com/workers-ai/configuration/open-ai-compatibility/ + - name: cohere.embed-english-v3 + type: embedding + input_price: 0.1 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 96 + - name: cohere.embed-multilingual-v3 + type: embedding + input_price: 0.1 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 96 + - name: us.meta.llama3-3-70b-instruct-v1:0 + type: chat + max_input_tokens: 131072 + input_price: 0.72 + output_price: 0.72 + max_output_tokens: 8192 + require_max_tokens: true + supports_function_calling: true + - name: us.amazon.nova-premier-v1:0 + type: chat + max_input_tokens: 300000 + input_price: 2.5 + output_price: 12.5 + max_output_tokens: 5120 + - name: us.amazon.nova-pro-v1:0 + type: chat + max_input_tokens: 300000 + input_price: 0.8 + output_price: 3.2 + max_output_tokens: 5120 + supports_vision: true + - name: us.amazon.nova-lite-v1:0 + type: chat + max_input_tokens: 300000 + input_price: 0.06 + output_price: 0.24 + max_output_tokens: 5120 + supports_vision: true + - name: us.amazon.nova-micro-v1:0 + type: chat + max_input_tokens: 128000 + input_price: 0.035 + output_price: 0.14 + max_output_tokens: 5120 + - name: anthropic.claude-fable-5-1 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: global.anthropic.claude-fable-5-1 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: us.anthropic.claude-fable-5-1 + type: chat + max_input_tokens: 1000000 + input_price: 11.0 + output_price: 55.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: xai.grok-4.6 + type: chat + max_input_tokens: 500000 + input_price: 2.2 + output_price: 6.6 + max_output_tokens: 500000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - name: anthropic.claude-opus-5 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: au.anthropic.claude-opus-5 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: eu.anthropic.claude-opus-5 + type: chat + max_input_tokens: 1000000 + input_price: 5.5 + output_price: 27.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: global.anthropic.claude-opus-5 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: jp.anthropic.claude-opus-5 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: us.anthropic.claude-opus-5 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: global.openai.gpt-5.6-luna + type: chat + max_input_tokens: 1050000 + input_price: 0.2 + output_price: 1.2 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + - name: global.openai.gpt-5.6-sol + type: chat + max_input_tokens: 1050000 + input_price: 4.0 + output_price: 20.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + - name: global.openai.gpt-5.6-terra + type: chat + max_input_tokens: 1050000 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + - name: openai.gpt-5.6-luna + type: chat + max_input_tokens: 1050000 + input_price: 0.22 + output_price: 1.32 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + - name: openai.gpt-5.6-sol + type: chat + max_input_tokens: 1050000 + input_price: 4.4 + output_price: 22.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + - name: openai.gpt-5.6-terra + type: chat + max_input_tokens: 1050000 + input_price: 2.2 + output_price: 13.2 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + - name: anthropic.claude-sonnet-5 + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: au.anthropic.claude-sonnet-5 + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: eu.anthropic.claude-sonnet-5 + type: chat + max_input_tokens: 1000000 + input_price: 2.2 + output_price: 11.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: global.anthropic.claude-sonnet-5 + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: jp.anthropic.claude-sonnet-5 + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: us.anthropic.claude-sonnet-5 + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic.claude-fable-5 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: eu.anthropic.claude-fable-5 + type: chat + max_input_tokens: 1000000 + input_price: 11.0 + output_price: 55.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: global.anthropic.claude-fable-5 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: us.anthropic.claude-fable-5 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic.claude-opus-4-8 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: au.anthropic.claude-opus-4-8 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: eu.anthropic.claude-opus-4-8 + type: chat + max_input_tokens: 1000000 + input_price: 5.5 + output_price: 27.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: global.anthropic.claude-opus-4-8 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: jp.anthropic.claude-opus-4-8 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: us.anthropic.claude-opus-4-8 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: openai.gpt-5.5 + type: chat + max_input_tokens: 272000 + input_price: 5.5 + output_price: 33.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - name: xai.grok-4.3 + type: chat + max_input_tokens: 1000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - name: anthropic.claude-opus-4-7 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: eu.anthropic.claude-opus-4-7 + type: chat + max_input_tokens: 1000000 + input_price: 5.5 + output_price: 27.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: global.anthropic.claude-opus-4-7 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: jp.anthropic.claude-opus-4-7 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + - name: us.anthropic.claude-opus-4-7 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: minimax.minimax-m2.5 + type: chat + max_input_tokens: 196608 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 98304 + supports_function_calling: true + - name: zai.glm-5 + type: chat + max_input_tokens: 202752 + input_price: 1.0 + output_price: 3.2 + max_output_tokens: 101376 + supports_function_calling: true + - name: nvidia.nemotron-super-3-120b + type: chat + max_input_tokens: 262144 + input_price: 0.15 + output_price: 0.65 + max_output_tokens: 131072 + supports_function_calling: true + - name: openai.gpt-5.4 + type: chat + max_input_tokens: 272000 + input_price: 2.75 + output_price: 16.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - name: anthropic.claude-sonnet-4-6 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: au.anthropic.claude-sonnet-4-6 + type: chat + max_input_tokens: 1000000 + input_price: 3.3 + output_price: 16.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: eu.anthropic.claude-sonnet-4-6 + type: chat + max_input_tokens: 1000000 + input_price: 3.3 + output_price: 16.5 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: global.anthropic.claude-sonnet-4-6 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: jp.anthropic.claude-sonnet-4-6 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: mistral.devstral-2-123b + type: chat + max_input_tokens: 256000 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 8192 + supports_function_calling: true + - name: us.anthropic.claude-sonnet-4-6 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + default_reasoning_effort: high + - name: us.anthropic.claude-sonnet-4-6:thinking + type: chat + real_name: us.anthropic.claude-sonnet-4-6 + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + patch: + body: + inferenceConfig: + temperature: null + topP: null + additionalModelRequestFields: + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + default_reasoning_effort: high + - name: deepseek.v3.2 + type: chat + max_input_tokens: 163840 + input_price: 0.62 + output_price: 1.85 + max_output_tokens: 81920 + supports_function_calling: true + - name: moonshotai.kimi-k2.5 + type: chat + max_input_tokens: 262143 + input_price: 0.6 + output_price: 3.0 + max_output_tokens: 16000 + supports_vision: true + supports_function_calling: true + - name: qwen.qwen3-coder-next + type: chat + max_input_tokens: 131072 + input_price: 0.22 + output_price: 1.8 + max_output_tokens: 65536 + supports_function_calling: true + - name: anthropic.claude-opus-4-6-v1 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: au.anthropic.claude-opus-4-6-v1 + type: chat + max_input_tokens: 1000000 + input_price: 16.5 + output_price: 82.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: eu.anthropic.claude-opus-4-6-v1 + type: chat + max_input_tokens: 1000000 + input_price: 5.5 + output_price: 27.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: global.anthropic.claude-opus-4-6-v1 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + - name: us.anthropic.claude-opus-4-6-v1 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + default_reasoning_effort: high + - name: us.anthropic.claude-opus-4-6-v1:thinking + type: chat + real_name: us.anthropic.claude-opus-4-6-v1 + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + patch: + body: + inferenceConfig: + temperature: null + topP: null + additionalModelRequestFields: + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + default_reasoning_effort: high + - name: zai.glm-4.7-flash + type: chat + max_input_tokens: 200000 + input_price: 0.07 + output_price: 0.4 + max_output_tokens: 131072 + supports_function_calling: true + - name: minimax.minimax-m2.1 + type: chat + max_input_tokens: 204800 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: nvidia.nemotron-nano-3-30b + type: chat + max_input_tokens: 128000 + input_price: 0.06 + output_price: 0.24 + max_output_tokens: 4096 + supports_function_calling: true + - name: zai.glm-4.7 + type: chat + max_input_tokens: 204800 + input_price: 0.6 + output_price: 2.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: mistral.magistral-small-2509 + type: chat + max_input_tokens: 128000 + input_price: 0.5 + output_price: 1.5 + max_output_tokens: 40000 + supports_vision: true + supports_function_calling: true + - name: mistral.ministral-3-3b-instruct + type: chat + max_input_tokens: 256000 + input_price: 0.1 + output_price: 0.1 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: mistral.mistral-large-3-675b-instruct + type: chat + max_input_tokens: 256000 + input_price: 0.5 + output_price: 1.5 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: moonshot.kimi-k2-thinking + type: chat + max_input_tokens: 262143 + input_price: 0.6 + output_price: 2.5 + max_output_tokens: 16000 + supports_function_calling: true + - name: anthropic.claude-opus-4-5-20251101-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: eu.anthropic.claude-opus-4-5-20251101-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 5.5 + output_price: 27.5 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: global.anthropic.claude-opus-4-5-20251101-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: us.anthropic.claude-opus-4-5-20251101-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: us.anthropic.claude-opus-4-5-20251101-v1:0:thinking + type: chat + real_name: us.anthropic.claude-opus-4-5-20251101-v1:0 + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + patch: + body: + inferenceConfig: + temperature: null + topP: null + additionalModelRequestFields: + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + - name: openai.gpt-oss-safeguard-120b + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 16384 + supports_function_calling: true + - name: openai.gpt-oss-safeguard-20b + type: chat + max_input_tokens: 128000 + input_price: 0.07 + output_price: 0.2 + max_output_tokens: 16384 + supports_function_calling: true + - name: minimax.minimax-m2 + type: chat + max_input_tokens: 204608 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 128000 + supports_function_calling: true + - name: anthropic.claude-haiku-4-5-20251001-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: au.anthropic.claude-haiku-4-5-20251001-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: eu.anthropic.claude-haiku-4-5-20251001-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 1.1 + output_price: 5.5 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: global.anthropic.claude-haiku-4-5-20251001-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: jp.anthropic.claude-haiku-4-5-20251001-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: us.anthropic.claude-haiku-4-5-20251001-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: us.anthropic.claude-haiku-4-5-20251001-v1:0:thinking + type: chat + real_name: us.anthropic.claude-haiku-4-5-20251001-v1:0 + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + patch: + body: + inferenceConfig: + temperature: null + topP: null + additionalModelRequestFields: + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + - name: qwen.qwen3-vl-235b-a22b + type: chat + max_input_tokens: 262000 + input_price: 0.3 + output_price: 1.5 + max_output_tokens: 262000 + supports_vision: true + supports_function_calling: true + - name: anthropic.claude-sonnet-4-5-20250929-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: au.anthropic.claude-sonnet-4-5-20250929-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: eu.anthropic.claude-sonnet-4-5-20250929-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 3.3 + output_price: 16.5 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: global.anthropic.claude-sonnet-4-5-20250929-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: jp.anthropic.claude-sonnet-4-5-20250929-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: us.anthropic.claude-sonnet-4-5-20250929-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: us.anthropic.claude-sonnet-4-5-20250929-v1:0:thinking + type: chat + real_name: us.anthropic.claude-sonnet-4-5-20250929-v1:0 + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + patch: + body: + inferenceConfig: + temperature: null + topP: null + additionalModelRequestFields: + thinking: + type: enabled + budget_tokens: 16000 + max_output_tokens: 24000 + require_max_tokens: true + supports_vision: true + - name: deepseek.v3-v1:0 + type: chat + max_input_tokens: 163840 + input_price: 0.58 + output_price: 1.68 + max_output_tokens: 81920 + supports_function_calling: true + - name: qwen.qwen3-235b-a22b-2507-v1:0 + type: chat + max_input_tokens: 262144 + input_price: 0.22 + output_price: 0.88 + max_output_tokens: 131072 + supports_function_calling: true + - name: qwen.qwen3-32b-v1:0 + type: chat + max_input_tokens: 16384 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 16384 + supports_function_calling: true + - name: qwen.qwen3-coder-30b-a3b-v1:0 + type: chat + max_input_tokens: 262144 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 131072 + supports_function_calling: true + - name: qwen.qwen3-coder-480b-a35b-v1:0 + type: chat + max_input_tokens: 131072 + input_price: 0.22 + output_price: 1.8 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen.qwen3-next-80b-a3b + type: chat + max_input_tokens: 262000 + input_price: 0.14 + output_price: 1.4 + max_output_tokens: 262000 + supports_function_calling: true + - name: anthropic.claude-opus-4-1-20250805-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + max_output_tokens: 32000 + supports_vision: true + supports_function_calling: true + - name: openai.gpt-oss-120b + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 16384 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: openai.gpt-oss-120b-1:0 + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 16384 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: openai.gpt-oss-20b + type: chat + max_input_tokens: 128000 + input_price: 0.07 + output_price: 0.3 + max_output_tokens: 16384 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: openai.gpt-oss-20b-1:0 + type: chat + max_input_tokens: 128000 + input_price: 0.07 + output_price: 0.3 + max_output_tokens: 16384 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: us.anthropic.claude-opus-4-1-20250805-v1:0 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + max_output_tokens: 32000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: google.gemma-3-27b-it + type: chat + max_input_tokens: 202752 + input_price: 0.12 + output_price: 0.2 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: mistral.voxtral-small-24b-2507 + type: chat + max_input_tokens: 32000 + input_price: 0.15 + output_price: 0.35 + max_output_tokens: 8192 + supports_function_calling: true + - name: writer.palmyra-x4-v1:0 + type: chat + max_input_tokens: 122880 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 8192 + supports_function_calling: true + - name: writer.palmyra-x5-v1:0 + type: chat + max_input_tokens: 1040000 + input_price: 0.6 + output_price: 6.0 + max_output_tokens: 8192 + supports_function_calling: true + - name: mistral.pixtral-large-2502-v1:0 + type: chat + max_input_tokens: 128000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: meta.llama4-maverick-17b-instruct-v1:0 + type: chat + max_input_tokens: 1000000 + input_price: 0.24 + output_price: 0.97 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: meta.llama4-scout-17b-instruct-v1:0 + type: chat + max_input_tokens: 3500000 + input_price: 0.17 + output_price: 0.66 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: us.meta.llama4-maverick-17b-instruct-v1:0 + type: chat + max_input_tokens: 1000000 + input_price: 0.24 + output_price: 0.97 + max_output_tokens: 16384 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: us.meta.llama4-scout-17b-instruct-v1:0 + type: chat + max_input_tokens: 3500000 + input_price: 0.17 + output_price: 0.66 + max_output_tokens: 16384 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: deepseek.r1-v1:0 + type: chat + max_input_tokens: 128000 + input_price: 1.35 + output_price: 5.4 + max_output_tokens: 32768 + supports_function_calling: true + - name: us.deepseek.r1-v1:0 + type: chat + max_input_tokens: 128000 + input_price: 1.35 + output_price: 5.4 + max_output_tokens: 32768 + supports_function_calling: true + - name: meta.llama3-3-70b-instruct-v1:0 + type: chat + max_input_tokens: 128000 + input_price: 0.72 + output_price: 0.72 + max_output_tokens: 4096 + supports_function_calling: true + - name: amazon.nova-lite-v1:0 + type: chat + max_input_tokens: 300000 + input_price: 0.06 + output_price: 0.24 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: amazon.nova-micro-v1:0 + type: chat + max_input_tokens: 128000 + input_price: 0.035 + output_price: 0.14 + max_output_tokens: 8192 + supports_function_calling: true + - name: amazon.nova-pro-v1:0 + type: chat + max_input_tokens: 300000 + input_price: 0.8 + output_price: 3.2 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: amazon.nova-2-lite-v1:0 + type: chat + max_input_tokens: 128000 + input_price: 0.33 + output_price: 2.75 + max_output_tokens: 4096 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: google.gemma-3-12b-it + type: chat + max_input_tokens: 131072 + input_price: 0.05 + output_price: 0.1 + max_output_tokens: 8192 + supports_vision: true + - name: google.gemma-3-4b-it + type: chat + max_input_tokens: 128000 + input_price: 0.04 + output_price: 0.08 + max_output_tokens: 4096 + supports_vision: true + supports_function_calling: true + - name: mistral.ministral-3-14b-instruct + type: chat + max_input_tokens: 128000 + input_price: 0.2 + output_price: 0.2 + max_output_tokens: 4096 + supports_function_calling: true + - name: mistral.ministral-3-8b-instruct + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.15 + max_output_tokens: 4096 + supports_function_calling: true + - name: mistral.voxtral-mini-3b-2507 + type: chat + max_input_tokens: 128000 + input_price: 0.04 + output_price: 0.04 + max_output_tokens: 4096 + supports_function_calling: true + - name: nvidia.nemotron-nano-12b-v2 + type: chat + max_input_tokens: 128000 + input_price: 0.2 + output_price: 0.6 + max_output_tokens: 4096 + supports_vision: true + supports_function_calling: true + - name: nvidia.nemotron-nano-9b-v2 + type: chat + max_input_tokens: 128000 + input_price: 0.06 + output_price: 0.23 + max_output_tokens: 4096 + supports_function_calling: true + - name: meta.llama3-1-70b-instruct-v1:0 + type: chat + max_input_tokens: 128000 + input_price: 0.72 + output_price: 0.72 + max_output_tokens: 4096 + supports_function_calling: true + - name: meta.llama3-1-8b-instruct-v1:0 + type: chat + max_input_tokens: 128000 + input_price: 0.22 + output_price: 0.22 + max_output_tokens: 4096 + supports_function_calling: true - provider: cloudflare models: - - name: '@cf/meta/llama-4-scout-17b-16e-instruct' - max_input_tokens: 131072 - max_output_tokens: 2048 - require_max_tokens: true - input_price: 0 - output_price: 0 - - name: '@cf/meta/llama-3.3-70b-instruct-fp8-fast' - max_input_tokens: 131072 - max_output_tokens: 2048 - require_max_tokens: true - input_price: 0 - output_price: 0 - - name: '@cf/qwen/qwen3-30b-a3b-fp8' - max_input_tokens: 131072 - max_output_tokens: 2048 - require_max_tokens: true - input_price: 0 - output_price: 0 - - name: '@cf/qwen/qwen2.5-coder-32b-instruct' - max_input_tokens: 131072 - max_output_tokens: 2048 - require_max_tokens: true - input_price: 0 - output_price: 0 - - name: '@cf/zai-org/glm-4.7-flash' - max_input_tokens: 131072 - max_output_tokens: 2048 - require_max_tokens: true - input_price: 0 - output_price: 0 - - name: '@cf/google/gemma-3-12b-it' - max_input_tokens: 131072 - max_output_tokens: 2048 - require_max_tokens: true - input_price: 0 - output_price: 0 - - name: '@cf/mistralai/mistral-small-3.1-24b-instruct' - max_input_tokens: 131072 - max_output_tokens: 2048 - require_max_tokens: true - input_price: 0 - output_price: 0 - - name: '@cf/baai/bge-large-en-v1.5' - type: embedding - input_price: 0 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 100 - -# Links: -# - https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j -# - https://cloud.baidu.com/doc/qianfan/s/wmh4sv6ya + - name: '@cf/baai/bge-large-en-v1.5' + type: embedding + input_price: 0.0 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 100 + - name: '@cf/google/gemma-3-12b-it' + type: chat + max_input_tokens: 131072 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 2048 + require_max_tokens: true + - name: '@cf/zai-org/glm-5.3-flash' + type: chat + max_input_tokens: 1310720 + input_price: 0.15 + output_price: 0.5 + max_output_tokens: 1048576 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: '@cf/qwen/qwen3.8-27b' + type: chat + max_input_tokens: 262144 + input_price: 0.45 + output_price: 3.2 + max_output_tokens: 262144 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - xhigh + - name: '@cf/zai-org/glm-5.3' + type: chat + max_input_tokens: 1310720 + input_price: 1.4 + output_price: 4.4 + max_output_tokens: 1310720 + require_max_tokens: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: '@cf/deepseek-ai/deepseek-v4-pro-0813' + type: chat + max_input_tokens: 1048576 + input_price: 1.32 + output_price: 3.96 + max_output_tokens: 1048576 + require_max_tokens: true + supports_function_calling: true + reasoning_levels: + - high + - max + - name: '@cf/deepseek-ai/deepseek-v4-flash-0731' + type: chat + max_input_tokens: 1310720 + input_price: 0.44 + output_price: 1.32 + max_output_tokens: 1048576 + require_max_tokens: true + supports_function_calling: true + reasoning_levels: + - high + - max + - name: '@cf/zai-org/glm-5.2' + type: chat + max_input_tokens: 262144 + input_price: 1.4 + output_price: 4.4 + max_output_tokens: 256000 + require_max_tokens: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: '@cf/moonshotai/kimi-k2.7-code' + type: chat + max_input_tokens: 262144 + input_price: 0.95 + output_price: 4.0 + max_output_tokens: 262144 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: '@cf/moonshotai/kimi-k2.6' + type: chat + max_input_tokens: 262144 + input_price: 0.95 + output_price: 4.0 + max_output_tokens: 256000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: '@cf/google/gemma-4-26b-a4b-it' + type: chat + max_input_tokens: 256000 + input_price: 0.1 + output_price: 0.3 + max_output_tokens: 16384 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: '@cf/nvidia/nemotron-3-120b-a12b' + type: chat + max_input_tokens: 256000 + input_price: 0.5 + output_price: 1.5 + max_output_tokens: 256000 + require_max_tokens: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: '@cf/zai-org/glm-4.7-flash' + type: chat + max_input_tokens: 131072 + input_price: 0.0605 + output_price: 0.4 + max_output_tokens: 131072 + require_max_tokens: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: '@cf/ibm-granite/granite-4.0-h-micro' + type: chat + max_input_tokens: 131000 + input_price: 0.017 + output_price: 0.112 + max_output_tokens: 131000 + require_max_tokens: true + supports_function_calling: true + - name: '@cf/aisingapore/gemma-sea-lion-v4-27b-it' + type: chat + max_input_tokens: 128000 + input_price: 0.351 + output_price: 0.555 + max_output_tokens: 128000 + require_max_tokens: true + - name: '@cf/openai/gpt-oss-120b' + type: chat + max_input_tokens: 128000 + input_price: 0.35 + output_price: 0.75 + max_output_tokens: 16384 + require_max_tokens: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: '@cf/openai/gpt-oss-20b' + type: chat + max_input_tokens: 128000 + input_price: 0.2 + output_price: 0.3 + max_output_tokens: 16384 + require_max_tokens: true + supports_function_calling: true + - name: '@cf/qwen/qwen3-30b-a3b-fp8' + type: chat + max_input_tokens: 32768 + input_price: 0.0509 + output_price: 0.335 + max_output_tokens: 32768 + require_max_tokens: true + supports_function_calling: true + - name: '@cf/meta/llama-4-scout-17b-16e-instruct' + type: chat + max_input_tokens: 131000 + input_price: 0.27 + output_price: 0.85 + max_output_tokens: 16384 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: '@cf/mistralai/mistral-small-3.1-24b-instruct' + type: chat + max_input_tokens: 128000 + input_price: 0.351 + output_price: 0.555 + max_output_tokens: 128000 + require_max_tokens: true + supports_function_calling: true + - name: '@cf/qwen/qwq-32b' + type: chat + max_input_tokens: 24000 + input_price: 0.66 + output_price: 1.0 + max_output_tokens: 24000 + require_max_tokens: true + - name: '@cf/deepseek-ai/deepseek-r1-distill-qwen-32b' + type: chat + max_input_tokens: 80000 + input_price: 0.497 + output_price: 4.881 + max_output_tokens: 80000 + require_max_tokens: true + - name: '@cf/meta/llama-3.3-70b-instruct-fp8-fast' + type: chat + max_input_tokens: 24000 + input_price: 0.293 + output_price: 2.253 + max_output_tokens: 24000 + require_max_tokens: true + supports_function_calling: true + - name: '@cf/qwen/qwen2.5-coder-32b-instruct' + type: chat + max_input_tokens: 32768 + input_price: 0.66 + output_price: 1.0 + max_output_tokens: 32768 + require_max_tokens: true + - name: '@cf/meta/llama-3.2-11b-vision-instruct' + type: chat + max_input_tokens: 128000 + input_price: 0.0485 + output_price: 0.676 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + - name: '@cf/meta/llama-3.2-1b-instruct' + type: chat + max_input_tokens: 60000 + input_price: 0.027 + output_price: 0.201 + max_output_tokens: 60000 + require_max_tokens: true + - name: '@cf/meta/llama-3.2-3b-instruct' + type: chat + max_input_tokens: 80000 + input_price: 0.0509 + output_price: 0.335 + max_output_tokens: 80000 + require_max_tokens: true + - name: '@cf/meta/llama-3.1-8b-instruct-fp8' + type: chat + max_input_tokens: 32000 + input_price: 0.152 + output_price: 0.287 + max_output_tokens: 32000 + require_max_tokens: true + - name: '@cf/meta/llama-guard-3-8b' + type: chat + max_input_tokens: 131072 + input_price: 0.484 + output_price: 0.03 + max_output_tokens: 131072 + require_max_tokens: true - provider: ernie models: - - name: ernie-4.5-turbo-128k - max_input_tokens: 131072 - input_price: 0.112 - output_price: 0.448 - - name: ernie-4.5-turbo-vl-32k - max_input_tokens: 32768 - input_price: 0.42 - output_price: 1.26 - supports_vision: true - - name: ernie-5.0-thinking-preview - max_input_tokens: 131072 - input_price: 1.4 - output_price: 5.6 - - name: ernie-x1.1-preview - max_input_tokens: 65536 - input_price: 0.14 - output_price: 0.56 - - name: bge-large-zh - type: embedding - input_price: 0.07 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 16 - - name: bge-large-en - type: embedding - input_price: 0.07 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 16 - - name: bce-reranker-base - type: reranker - max_input_tokens: 1024 - input_price: 0.07 - -# Links: -# - https://help.aliyun.com/zh/model-studio/getting-started/models -# - https://help.aliyun.com/zh/model-studio/developer-reference/use-qwen-by-calling-api + - name: ernie-4.5-turbo-128k + type: chat + max_input_tokens: 131072 + input_price: 0.112 + output_price: 0.448 + - name: ernie-4.5-turbo-vl-32k + type: chat + max_input_tokens: 32768 + input_price: 0.42 + output_price: 1.26 + supports_vision: true + - name: ernie-5.0-thinking-preview + type: chat + max_input_tokens: 131072 + input_price: 1.4 + output_price: 5.6 + - name: ernie-x1.1-preview + type: chat + max_input_tokens: 65536 + input_price: 0.14 + output_price: 0.56 + - name: bge-large-zh + type: embedding + input_price: 0.07 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 16 + - name: bge-large-en + type: embedding + input_price: 0.07 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 16 + - name: bce-reranker-base + type: reranker + max_input_tokens: 1024 + input_price: 0.07 - provider: qianwen models: - - name: qwen3.5-plus - max_input_tokens: 262144 - supports_function_calling: true - patch: - body: - enable_thinking: false - - name: qwen3.5-plus:thinking - real_name: qwen3.5-plus - max_input_tokens: 262144 - supports_function_calling: true - - name: qwen3-max - max_input_tokens: 262144 - supports_function_calling: true - - name: qwen3-max:thinking - real_name: qwen3-max - max_input_tokens: 262144 - supports_function_calling: true - patch: - body: - enable_thinking: true - - name: qwen3-vl-plus - max_input_tokens: 262144 - supports_vision: true - - name: qwen3-vl-flash - max_input_tokens: 262144 - supports_vision: true - - name: qwen3-coder-plus - max_input_tokens: 1000000 - - name: qwen3-coder-flash - max_input_tokens: 1000000 - - name: qwen3.5-397b-a17b - max_input_tokens: 262144 - supports_function_calling: true - patch: - body: - enable_thinking: false - - name: qwen3.5-397b-a17b:thinking - real_name: qwen3.5-397b-a17b - max_input_tokens: 262144 - supports_function_calling: true - - name: qwen3-next-80b-a3b-instruct - max_input_tokens: 131072 - input_price: 0.14 - output_price: 0.56 - supports_function_calling: true - - name: qwen3-next-80b-a3b-thinking - max_input_tokens: 131072 - input_price: 0.14 - output_price: 1.4 - - name: qwen3-235b-a22b-instruct-2507 - max_input_tokens: 131072 - input_price: 0.28 - output_price: 1.12 - supports_function_calling: true - - name: qwen3-235b-a22b-thinking-2507 - max_input_tokens: 131072 - input_price: 0.28 - output_price: 2.8 - - name: qwen3-30b-a3b-instruct-2507 - max_input_tokens: 131072 - input_price: 0.105 - output_price: 0.42 - supports_function_calling: true - - name: qwen3-30b-a3b-thinking-2507 - max_input_tokens: 131072 - input_price: 0.105 - output_price: 1.05 - - name: qwen3-vl-32b-instruct - max_input_tokens: 131072 - input_price: 0.28 - output_price: 1.12 - supports_vision: true - - name: qwen3-vl-8b-instruct - max_input_tokens: 131072 - input_price: 0.07 - output_price: 0.28 - supports_vision: true - - name: qwen3-coder-next - max_input_tokens: 262144 - - name: qwen3-coder-480b-a35b-instruct - max_input_tokens: 262144 - - name: qwen3-coder-30b-a3b-instruct - max_input_tokens: 262144 - - name: text-embedding-v4 - type: embedding - input_price: 0.1 - max_tokens_per_chunk: 8192 - default_chunk_size: 2000 - max_batch_size: 10 - - name: text-embedding-v3 - type: embedding - input_price: 0.1 - max_tokens_per_chunk: 8192 - default_chunk_size: 2000 - max_batch_size: 10 - -# links: -# - https://cloud.tencent.com/document/product/1729/104753 -# - https://cloud.tencent.com/document/product/1729/97731 -# - https://cloud.tencent.com/document/product/1729/111007 + - name: qwen3.5-plus:thinking + type: chat + real_name: qwen3.5-plus + max_input_tokens: 262144 + supports_function_calling: true + - name: qwen3.5-397b-a17b:thinking + type: chat + real_name: qwen3.5-397b-a17b + max_input_tokens: 262144 + supports_function_calling: true + - name: text-embedding-v4 + type: embedding + input_price: 0.1 + max_tokens_per_chunk: 8192 + default_chunk_size: 2000 + max_batch_size: 10 + - name: text-embedding-v3 + type: embedding + input_price: 0.1 + max_tokens_per_chunk: 8192 + default_chunk_size: 2000 + max_batch_size: 10 + - name: qwen3-vl-flash + type: chat + max_input_tokens: 262144 + supports_vision: true + - name: qwen3-235b-a22b-instruct-2507 + type: chat + max_input_tokens: 131072 + input_price: 0.28 + output_price: 1.12 + supports_function_calling: true + - name: qwen3-235b-a22b-thinking-2507 + type: chat + max_input_tokens: 131072 + input_price: 0.28 + output_price: 2.8 + - name: qwen3-30b-a3b-instruct-2507 + type: chat + max_input_tokens: 131072 + input_price: 0.105 + output_price: 0.42 + supports_function_calling: true + - name: qwen3-30b-a3b-thinking-2507 + type: chat + max_input_tokens: 131072 + input_price: 0.105 + output_price: 1.05 + - name: qwen3-vl-32b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.28 + output_price: 1.12 + supports_vision: true + - name: qwen3-vl-8b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.07 + output_price: 0.28 + supports_vision: true + - name: qwen3-coder-next + type: chat + max_input_tokens: 262144 + - name: qwen3.8-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.15 + output_price: 0.47 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - xhigh + - name: qwen3.8-max + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - xhigh + - name: deepseek-v4-flash-0731 + type: chat + max_input_tokens: 1000000 + input_price: 0.2 + output_price: 0.4 + max_output_tokens: 384000 + supports_function_calling: true + reasoning_levels: + - high + - max + - name: glm-5.2 + type: chat + max_input_tokens: 1000000 + input_price: 1.4 + output_price: 4.4 + max_output_tokens: 131072 + supports_function_calling: true + reasoning_levels: + - none + - minimal + - low + - medium + - high + - xhigh + - max + - name: qwen3.7-plus + type: chat + max_input_tokens: 1000000 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3.7-max + type: chat + max_input_tokens: 1000000 + input_price: 2.5 + output_price: 7.5 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen3.6-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.1875 + output_price: 1.125 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3.6-27b + type: chat + max_input_tokens: 262144 + input_price: 0.6 + output_price: 3.6 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3.6-max-preview + type: chat + max_input_tokens: 262144 + input_price: 1.3 + output_price: 7.8 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen3.6-35b-a3b + type: chat + max_input_tokens: 262144 + input_price: 0.248 + output_price: 1.485 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3.6-plus + type: chat + max_input_tokens: 1000000 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3.5-122b-a10b + type: chat + max_input_tokens: 262144 + input_price: 0.4 + output_price: 3.2 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3.5-27b + type: chat + max_input_tokens: 262144 + input_price: 0.3 + output_price: 2.4 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3.5-35b-a3b + type: chat + max_input_tokens: 262144 + input_price: 0.25 + output_price: 2.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3.5-plus + type: chat + max_input_tokens: 1000000 + input_price: 0.4 + output_price: 2.4 + patch: + body: + enable_thinking: false + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3.5-397b-a17b + type: chat + max_input_tokens: 262144 + input_price: 0.6 + output_price: 3.6 + patch: + body: + enable_thinking: false + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen3-max + type: chat + max_input_tokens: 262144 + input_price: 1.2 + output_price: 6.0 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen3-max:thinking + type: chat + real_name: qwen3-max + max_input_tokens: 262144 + input_price: 1.2 + output_price: 6.0 + patch: + body: + enable_thinking: true + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen3-vl-plus + type: chat + max_input_tokens: 262144 + input_price: 0.2 + output_price: 1.6 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: qwen3-omni-flash + type: chat + max_input_tokens: 65536 + input_price: 0.43 + output_price: 1.66 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: qwen3-asr-flash + type: chat + max_input_tokens: 53248 + input_price: 0.035 + output_price: 0.035 + max_output_tokens: 4096 + - name: qwen3-next-80b-a3b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.5 + output_price: 2.0 + max_output_tokens: 32768 + supports_function_calling: true + - name: qwen3-next-80b-a3b-thinking + type: chat + max_input_tokens: 131072 + input_price: 0.5 + output_price: 6.0 + max_output_tokens: 32768 + supports_function_calling: true + - name: qwen-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.05 + output_price: 0.4 + max_output_tokens: 32768 + supports_function_calling: true + - name: qwen3-coder-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.3 + output_price: 1.5 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen3-coder-plus + type: chat + max_input_tokens: 1048576 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen3-14b + type: chat + max_input_tokens: 131072 + input_price: 0.35 + output_price: 1.4 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen3-235b-a22b + type: chat + max_input_tokens: 131072 + input_price: 0.7 + output_price: 2.8 + max_output_tokens: 16384 + supports_function_calling: true + - name: qwen3-32b + type: chat + max_input_tokens: 131072 + input_price: 0.7 + output_price: 2.8 + max_output_tokens: 16384 + supports_function_calling: true + - name: qwen3-8b + type: chat + max_input_tokens: 131072 + input_price: 0.18 + output_price: 0.7 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen3-coder-30b-a3b-instruct + type: chat + max_input_tokens: 262144 + input_price: 0.45 + output_price: 2.25 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen3-coder-480b-a35b-instruct + type: chat + max_input_tokens: 262144 + input_price: 1.5 + output_price: 7.5 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen3-vl-235b-a22b + type: chat + max_input_tokens: 131072 + input_price: 0.7 + output_price: 2.8 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: qwen3-vl-30b-a3b + type: chat + max_input_tokens: 131072 + input_price: 0.2 + output_price: 0.8 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: qvq-max + type: chat + max_input_tokens: 131072 + input_price: 1.2 + output_price: 4.8 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: qwq-plus + type: chat + max_input_tokens: 131072 + input_price: 0.8 + output_price: 2.4 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen-omni-turbo + type: chat + max_input_tokens: 32768 + input_price: 0.07 + output_price: 0.27 + max_output_tokens: 2048 + supports_vision: true + supports_function_calling: true + - name: qwen-mt-plus + type: chat + max_input_tokens: 16384 + input_price: 2.46 + output_price: 7.37 + max_output_tokens: 8192 + - name: qwen-mt-turbo + type: chat + max_input_tokens: 16384 + input_price: 0.16 + output_price: 0.49 + max_output_tokens: 8192 + - name: qwen2-5-omni-7b + type: chat + max_input_tokens: 32768 + input_price: 0.1 + output_price: 0.4 + max_output_tokens: 2048 + supports_vision: true + supports_function_calling: true + - name: qwen-turbo + type: chat + max_input_tokens: 1000000 + input_price: 0.05 + output_price: 0.2 + max_output_tokens: 16384 + supports_function_calling: true + - name: qwen-vl-ocr + type: chat + max_input_tokens: 34096 + input_price: 0.72 + output_price: 0.72 + max_output_tokens: 4096 + supports_vision: true + - name: qwen2-5-14b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.35 + output_price: 1.4 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen2-5-32b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.7 + output_price: 2.8 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen2-5-72b-instruct + type: chat + max_input_tokens: 131072 + input_price: 1.4 + output_price: 5.6 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen2-5-7b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.175 + output_price: 0.7 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen2-5-vl-72b-instruct + type: chat + max_input_tokens: 131072 + input_price: 2.8 + output_price: 8.4 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: qwen2-5-vl-7b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.35 + output_price: 1.05 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: qwen-vl-max + type: chat + max_input_tokens: 131072 + input_price: 0.8 + output_price: 3.2 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: qwen-max + type: chat + max_input_tokens: 32768 + input_price: 1.6 + output_price: 6.4 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen-plus + type: chat + max_input_tokens: 1000000 + input_price: 0.4 + output_price: 1.2 + max_output_tokens: 32768 + supports_function_calling: true + - name: qwen-vl-plus + type: chat + max_input_tokens: 131072 + input_price: 0.21 + output_price: 0.63 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: qwen-plus-character-ja + type: chat + max_input_tokens: 8192 + input_price: 0.5 + output_price: 1.4 + max_output_tokens: 512 + supports_function_calling: true - provider: hunyuan models: - - name: hunyuan-2.0-instruct-20251111 - max_input_tokens: 131072 - input_price: 0.112 - output_price: 0.28 - supports_function_calling: true - - name: hunyuan-2.0-thinking-20251109 - max_input_tokens: 131072 - input_price: 0.14 - output_price: 0.56 - supports_function_calling: true - - name: hunyuan-vision-1.5-instruct - max_input_tokens: 24576 - input_price: 0.42 - output_price: 1.26 - supports_vision: true - - name: hunyuan-embedding - type: embedding - input_price: 0.01 - max_tokens_per_chunk: 1024 - default_chunk_size: 1000 - max_batch_size: 100 - -# Links: -# - https://platform.moonshot.cn/docs/pricing/chat#%E8%AE%A1%E8%B4%B9%E5%9F%BA%E6%9C%AC%E6%A6%82%E5%BF%B5 -# - https://platform.moonshot.cn/docs/api/chat#%E5%85%AC%E5%BC%80%E7%9A%84%E6%9C%8D%E5%8A%A1%E5%9C%B0%E5%9D%80 + - name: hunyuan-2.0-instruct-20251111 + type: chat + max_input_tokens: 131072 + input_price: 0.112 + output_price: 0.28 + supports_function_calling: true + - name: hunyuan-2.0-thinking-20251109 + type: chat + max_input_tokens: 131072 + input_price: 0.14 + output_price: 0.56 + supports_function_calling: true + - name: hunyuan-vision-1.5-instruct + type: chat + max_input_tokens: 24576 + input_price: 0.42 + output_price: 1.26 + supports_vision: true + - name: hunyuan-embedding + type: embedding + input_price: 0.01 + max_tokens_per_chunk: 1024 + default_chunk_size: 1000 + max_batch_size: 100 - provider: moonshot models: - - name: kimi-k3 - max_input_tokens: 1048576 - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - - name: kimi-k2.7-code - max_input_tokens: 262144 - input_price: 0.95 - output_price: 4 - supports_vision: true - supports_function_calling: true - - name: kimi-k2.7-code-highspeed - max_input_tokens: 262144 - input_price: 1.9 - output_price: 8 - supports_vision: true - supports_function_calling: true - - name: kimi-k2.6 - max_input_tokens: 262144 - input_price: 0.95 - output_price: 4 - supports_vision: true - supports_function_calling: true - - name: kimi-k2.5 - max_input_tokens: 262144 - input_price: 0.56 - output_price: 2.94 - supports_vision: true - supports_function_calling: true - - name: kimi-k2-turbo-preview - max_input_tokens: 262144 - input_price: 1.12 - output_price: 8.12 - supports_vision: true - supports_function_calling: true - - name: kimi-k2-0905-preview - max_input_tokens: 262144 - input_price: 0.56 - output_price: 2.24 - supports_vision: true - supports_function_calling: true - - name: kimi-k2-thinking-turbo - max_input_tokens: 262144 - input_price: 1.12 - output_price: 8.12 - supports_vision: true - - name: kimi-k2-thinking - max_input_tokens: 262144 - input_price: 0.56 - output_price: 2.24 - supports_vision: true - -# Links: -# - https://api-docs.deepseek.com/quick_start/pricing -# - https://platform.deepseek.com/api-docs/api/create-chat-completion + - name: kimi-k3 + type: chat + max_input_tokens: 1048576 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + - max + - name: kimi-k2.7-code + type: chat + max_input_tokens: 262144 + input_price: 0.95 + output_price: 4.0 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: kimi-k2.7-code-highspeed + type: chat + max_input_tokens: 262144 + input_price: 1.9 + output_price: 8.0 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: kimi-k2.6 + type: chat + max_input_tokens: 262144 + input_price: 0.95 + output_price: 4.0 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: kimi-k2.5 + type: chat + max_input_tokens: 262144 + input_price: 0.6 + output_price: 3.0 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: kimi-k2-thinking + type: chat + max_input_tokens: 262144 + input_price: 0.6 + output_price: 2.5 + max_output_tokens: 262144 + supports_function_calling: true + - name: kimi-k2-thinking-turbo + type: chat + max_input_tokens: 262144 + input_price: 1.15 + output_price: 8.0 + max_output_tokens: 262144 + supports_function_calling: true + - name: kimi-k2-0905-preview + type: chat + max_input_tokens: 262144 + input_price: 0.6 + output_price: 2.5 + max_output_tokens: 262144 + supports_function_calling: true + - name: kimi-k2-turbo-preview + type: chat + max_input_tokens: 262144 + input_price: 2.4 + output_price: 10.0 + max_output_tokens: 262144 + supports_function_calling: true + - name: kimi-k2-0711-preview + type: chat + max_input_tokens: 131072 + input_price: 0.6 + output_price: 2.5 + max_output_tokens: 16384 + supports_function_calling: true - provider: deepseek models: - - name: deepseek-v4-pro - max_input_tokens: 1000000 - max_output_tokens: 384000 - input_price: 0.435 - output_price: 0.87 - supports_function_calling: true - - name: deepseek-v4-flash - max_input_tokens: 1000000 - max_output_tokens: 384000 - input_price: 0.14 - output_price: 0.28 - supports_function_calling: true - - name: deepseek-chat - max_input_tokens: 64000 - max_output_tokens: 8192 - input_price: 0.56 - output_price: 1.68 - supports_function_calling: true - - name: deepseek-reasoner - max_input_tokens: 64000 - max_output_tokens: 32768 - input_price: 0.56 - output_price: 1.68 - -# Links: -# - https://open.bigmodel.cn/pricing -# - https://open.bigmodel.cn/dev/api#glm-4 + - name: deepseek-chat + type: chat + max_input_tokens: 64000 + input_price: 0.56 + output_price: 1.68 + max_output_tokens: 8192 + supports_function_calling: true + - name: deepseek-reasoner + type: chat + max_input_tokens: 64000 + input_price: 0.56 + output_price: 1.68 + max_output_tokens: 32768 + - name: deepseek-v4-flash-vision-exp + type: chat + max_input_tokens: 1000000 + input_price: 0.14 + output_price: 0.28 + max_output_tokens: 384000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + - max + - name: deepseek-v4-pro + type: chat + max_input_tokens: 1000000 + input_price: 0.435 + output_price: 0.87 + max_output_tokens: 384000 + supports_function_calling: true + reasoning_levels: + - high + - max + - name: deepseek-v4-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.14 + output_price: 0.28 + max_output_tokens: 384000 + supports_function_calling: true + reasoning_levels: + - low + - high + - max - provider: zhipuai models: - - name: glm-5 - max_input_tokens: 202752 - supports_function_calling: true - - name: glm-5:instruct - real_name: glm-5 - max_input_tokens: 202752 - supports_function_calling: true - patch: - body: - thinking: - type: disabled - - name: glm-4.7 - max_input_tokens: 202752 - supports_function_calling: true - - name: glm-4.7:instruct - real_name: glm-4.7 - max_input_tokens: 202752 - supports_function_calling: true - patch: - body: - thinking: - type: disabled - - name: glm-4.7-flash - max_input_tokens: 202752 - input_price: 0 - output_price: 0 - supports_function_calling: true - - name: glm-4.6v - max_input_tokens: 65536 - supports_vision: true - - name: glm-4.6v-flash - max_input_tokens: 65536 - input_price: 0 - output_price: 0 - supports_vision: true - - name: embedding-3 - type: embedding - max_input_tokens: 8192 - input_price: 0.07 - max_tokens_per_chunk: 8192 - default_chunk_size: 2000 - - name: rerank - type: reranker - max_input_tokens: 4096 - input_price: 0.112 - -# Links: -# - https://platform.minimaxi.com/docs/guides/pricing-paygo -# - https://platform.minimaxi.com/document/ChatCompletion%20v2 + - name: embedding-3 + type: embedding + max_input_tokens: 8192 + input_price: 0.07 + max_tokens_per_chunk: 8192 + default_chunk_size: 2000 + - name: rerank + type: reranker + max_input_tokens: 4096 + input_price: 0.112 + - name: glm-4.6v-flash + type: chat + max_input_tokens: 65536 + input_price: 0.0 + output_price: 0.0 + supports_vision: true + - name: glm-5.3-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.075 + output_price: 0.25 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + - max + - name: glm-5.3 + type: chat + max_input_tokens: 1000000 + input_price: 1.4 + output_price: 4.4 + max_output_tokens: 131072 + supports_function_calling: true + reasoning_levels: + - low + - high + - max + - name: glm-5.2 + type: chat + max_input_tokens: 1000000 + input_price: 1.4 + output_price: 4.4 + max_output_tokens: 131072 + supports_function_calling: true + reasoning_levels: + - high + - max + - name: glm-5v-turbo + type: chat + max_input_tokens: 200000 + input_price: 5.0 + output_price: 22.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: glm-5.1 + type: chat + max_input_tokens: 200000 + input_price: 1.4 + output_price: 4.4 + max_output_tokens: 131072 + supports_function_calling: true + - name: glm-5 + type: chat + max_input_tokens: 204800 + input_price: 1.0 + output_price: 3.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: glm-5:instruct + type: chat + real_name: glm-5 + max_input_tokens: 204800 + input_price: 1.0 + output_price: 3.2 + patch: + body: + thinking: + type: disabled + max_output_tokens: 131072 + supports_function_calling: true + - name: glm-4.7-flash + type: chat + max_input_tokens: 200000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 131072 + supports_function_calling: true + - name: glm-4.7-flashx + type: chat + max_input_tokens: 200000 + input_price: 0.07 + output_price: 0.4 + max_output_tokens: 131072 + supports_function_calling: true + - name: glm-4.7 + type: chat + max_input_tokens: 204800 + input_price: 0.6 + output_price: 2.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: glm-4.7:instruct + type: chat + real_name: glm-4.7 + max_input_tokens: 204800 + input_price: 0.6 + output_price: 2.2 + patch: + body: + thinking: + type: disabled + max_output_tokens: 131072 + supports_function_calling: true + - name: glm-4.6v + type: chat + max_input_tokens: 128000 + input_price: 0.3 + output_price: 0.9 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: glm-4.6 + type: chat + max_input_tokens: 204800 + input_price: 0.6 + output_price: 2.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: glm-4.5v + type: chat + max_input_tokens: 64000 + input_price: 0.6 + output_price: 1.8 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: glm-4.5 + type: chat + max_input_tokens: 131072 + input_price: 0.6 + output_price: 2.2 + max_output_tokens: 98304 + supports_function_calling: true + - name: glm-4.5-air + type: chat + max_input_tokens: 131072 + input_price: 0.2 + output_price: 1.1 + max_output_tokens: 98304 + supports_function_calling: true + - name: glm-4.5-flash + type: chat + max_input_tokens: 131072 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 98304 + supports_function_calling: true - provider: minimax models: - - name: minimax-m3 - max_input_tokens: 1000000 - input_price: 4.2 - output_price: 16.8 - supports_function_calling: true - - name: minimax-m2.7 - max_input_tokens: 204800 - input_price: 0.294 - output_price: 1.176 - supports_function_calling: true - - name: minimax-m2.5 - max_input_tokens: 204800 - input_price: 0.294 - output_price: 1.176 - supports_function_calling: true - - name: minimax-m2.5-highspeed - max_input_tokens: 204800 - input_price: 0.588 - output_price: 2.352 - supports_function_calling: true - - name: minimax-m2.1 - max_input_tokens: 204800 - input_price: 0.294 - output_price: 1.176 - supports_function_calling: true - - name: minimax-m2.1-highspeed - max_input_tokens: 204800 - input_price: 0.588 - output_price: 2.352 - supports_function_calling: true - -# Links: -# - https://openrouter.ai/models -# - https://openrouter.ai/docs/api-reference/chat-completion + - name: minimax-m3 + type: chat + max_input_tokens: 1000000 + input_price: 4.2 + output_price: 16.8 + supports_function_calling: true + - name: minimax-m2.7 + type: chat + max_input_tokens: 204800 + input_price: 0.294 + output_price: 1.176 + supports_function_calling: true + - name: minimax-m2.5 + type: chat + max_input_tokens: 204800 + input_price: 0.294 + output_price: 1.176 + supports_function_calling: true + - name: minimax-m2.5-highspeed + type: chat + max_input_tokens: 204800 + input_price: 0.588 + output_price: 2.352 + supports_function_calling: true + - name: minimax-m2.1 + type: chat + max_input_tokens: 204800 + input_price: 0.294 + output_price: 1.176 + supports_function_calling: true + - name: minimax-m2.1-highspeed + type: chat + max_input_tokens: 204800 + input_price: 0.588 + output_price: 2.352 + supports_function_calling: true + - name: MiniMax-M3 + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 512000 + supports_vision: true + supports_function_calling: true + - name: MiniMax-M2.7 + type: chat + max_input_tokens: 204800 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: MiniMax-M2.7-highspeed + type: chat + max_input_tokens: 204800 + input_price: 0.6 + output_price: 2.4 + max_output_tokens: 131072 + supports_function_calling: true + - name: MiniMax-M2.5-highspeed + type: chat + max_input_tokens: 204800 + input_price: 0.6 + output_price: 2.4 + max_output_tokens: 131072 + supports_function_calling: true + - name: MiniMax-M2.5 + type: chat + max_input_tokens: 204800 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: MiniMax-M2.1 + type: chat + max_input_tokens: 204800 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: MiniMax-M2 + type: chat + max_input_tokens: 204800 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 131072 + supports_function_calling: true - provider: openrouter models: - - name: openai/gpt-5.6-sol - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 5 - output_price: 30 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh, max] - default_reasoning_effort: medium - - name: openai/gpt-5.6-terra - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 5 - output_price: 30 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh, max] - default_reasoning_effort: medium - - name: openai/gpt-5.6-luna - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 5 - output_price: 30 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh, max] - default_reasoning_effort: medium - - name: openai/gpt-5.5 - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 5 - output_price: 30 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: medium - - name: openai/gpt-5.5-pro - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 30 - output_price: 180 - supports_vision: true - supports_function_calling: true - reasoning_levels: [medium, high, xhigh] - default_reasoning_effort: high - - name: openai/gpt-5.4 - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 2.5 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: none - - name: openai/gpt-5.4-pro - max_input_tokens: 1050000 - max_output_tokens: 128000 - input_price: 30 - output_price: 180 - supports_vision: true - supports_function_calling: true - reasoning_levels: [medium, high, xhigh] - default_reasoning_effort: medium - - name: openai/gpt-5.4-mini - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 0.75 - output_price: 4.5 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: none - - name: openai/gpt-5.4-nano - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 0.2 - output_price: 1.25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: none - - name: openai/gpt-5.3-codex - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.75 - output_price: 14 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh] - default_reasoning_effort: medium - - name: openai/gpt-5.2 - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.75 - output_price: 14 - supports_vision: true - supports_function_calling: true - reasoning_levels: [none, low, medium, high, xhigh] - default_reasoning_effort: none - - name: openai/gpt-5.2-pro - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 21 - output_price: 168 - supports_vision: true - supports_function_calling: true - reasoning_levels: [medium, high, xhigh] - default_reasoning_effort: medium - - name: openai/gpt-5 - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: medium - - name: openai/gpt-5-mini - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 0.25 - output_price: 2 - supports_vision: true - supports_function_calling: true - - name: openai/gpt-5-nano - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 0.05 - output_price: 0.4 - supports_vision: true - supports_function_calling: true - - name: openai/gpt-4.1 - max_input_tokens: 1047576 - max_output_tokens: 32768 - input_price: 2 - output_price: 8 - supports_vision: true - supports_function_calling: true - - name: openai/gpt-4o - max_input_tokens: 128000 - input_price: 2.5 - output_price: 10 - supports_vision: true - supports_function_calling: true - - name: openai/gpt-oss-120b - max_input_tokens: 131072 - input_price: 0.09 - output_price: 0.45 - supports_function_calling: true - - name: openai/gpt-oss-20b - max_input_tokens: 131072 - input_price: 0.04 - output_price: 0.16 - supports_function_calling: true - - name: google/gemini-3.5-flash - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: medium - - name: google/gemini-3-flash-preview - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: high - - name: google/gemini-3.1-flash-lite - max_input_tokens: 1048576 - max_output_tokens: 65536 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_effort: minimal - - name: google/gemini-3.1-pro-preview - max_input_tokens: 1048576 - max_output_tokens: 65535 - input_price: 0.3 - output_price: 2.5 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high] - default_reasoning_effort: high - - name: google/gemini-3-pro-preview - max_input_tokens: 1048576 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, high] - default_reasoning_level: high - - name: google/gemini-3-flash-preview - max_input_tokens: 1048576 - supports_vision: true - supports_function_calling: true - reasoning_levels: [minimal, low, medium, high] - default_reasoning_level: high - - name: google/gemini-2.5-flash - max_input_tokens: 1048576 - input_price: 0.3 - output_price: 2.5 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high] - default_reasoning_effort: low - - name: google/gemini-2.5-pro - max_input_tokens: 1048576 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high] - default_reasoning_effort: high - - name: google/gemini-2.5-flash-lite - max_input_tokens: 1048576 - input_price: 0.3 - output_price: 0.4 - supports_vision: true - - name: google/gemini-2.0-flash-001 - max_input_tokens: 1000000 - input_price: 0.15 - output_price: 0.6 - supports_vision: true - supports_function_calling: true - - name: google/gemini-2.0-flash-lite-001 - max_input_tokens: 1048576 - input_price: 0.075 - output_price: 0.3 - supports_vision: true - supports_function_calling: true - - name: google/gemma-3-27b-it - max_input_tokens: 131072 - input_price: 0.1 - output_price: 0.2 - - name: anthropic/claude-opus-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: anthropic/claude-fable-5-1 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 10 - output_price: 50 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: anthropic/claude-fable-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 10 - output_price: 50 - supports_function_calling: true - supports_vision: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: anthropic/claude-opus-4-8 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: anthropic/claude-opus-4-7 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: anthropic/claude-opus-4.6 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, max] - default_reasoning_effort: high - - name: anthropic/claude-sonnet-5 - max_input_tokens: 1000000 - max_output_tokens: 128000 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, xhigh, max] - default_reasoning_effort: high - - name: anthropic/claude-sonnet-4.6 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - reasoning_levels: [low, medium, high, max] - default_reasoning_effort: high - - name: anthropic/claude-opus-4.5 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 5 - output_price: 25 - supports_vision: true - supports_function_calling: true - - name: anthropic/claude-sonnet-4.5 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 3 - output_price: 15 - supports_vision: true - supports_function_calling: true - - name: anthropic/claude-haiku-4.5 - max_input_tokens: 200000 - max_output_tokens: 8192 - require_max_tokens: true - input_price: 1 - output_price: 5 - supports_vision: true - supports_function_calling: true - - name: meta-llama/llama-4-maverick - max_input_tokens: 1048576 - input_price: 0.18 - output_price: 0.6 - supports_vision: true - supports_function_calling: true - - name: meta-llama/llama-4-scout - max_input_tokens: 327680 - input_price: 0.08 - output_price: 0.3 - supports_vision: true - supports_function_calling: true - - name: meta-llama/llama-3.3-70b-instruct - max_input_tokens: 131072 - input_price: 0.12 - output_price: 0.3 - - name: mistralai/mistral-large-2512 - max_input_tokens: 262144 - input_price: 0.5 - output_price: 1.5 - supports_function_calling: true - - name: mistralai/mistral-medium-3.1 - max_input_tokens: 131072 - input_price: 0.4 - output_price: 2 - supports_function_calling: true - supports_vision: true - - name: mistralai/mistral-small-3.2-24b-instruct - max_input_tokens: 131072 - input_price: 0.1 - output_price: 0.3 - supports_vision: true - - name: mistralai/devstral-2512 - max_input_tokens: 262144 - input_price: 0.5 - output_price: 0.22 - supports_function_calling: true - - name: mistralai/devstral-small - max_input_tokens: 131072 - input_price: 0.07 - output_price: 0.28 - supports_function_calling: true - - name: mistralai/codestral-2508 - max_input_tokens: 256000 - input_price: 0.3 - output_price: 0.9 - supports_function_calling: true - - name: mistralai/ministral-14b-2512 - max_input_tokens: 262144 - input_price: 0.2 - output_price: 0.2 - supports_function_calling: true - - name: ai21/jamba-large-1.7 - max_input_tokens: 256000 - input_price: 2 - output_price: 8 - supports_function_calling: true - - name: cohere/command-a - max_input_tokens: 256000 - input_price: 2.5 - output_price: 10 - supports_function_calling: true - - name: cohere/command-r7b-12-2024 - max_input_tokens: 128000 - max_output_tokens: 4096 - input_price: 0.0375 - output_price: 0.15 - - name: deepseek/deepseek-v3.2 - max_input_tokens: 163840 - input_price: 0.25 - output_price: 0.38 - - name: qwen/qwen3-max - max_input_tokens: 262144 - input_price: 1.2 - output_price: 6 - supports_function_calling: true - - name: qwen/qwen3-max-thinking - max_input_tokens: 262144 - input_price: 1.2 - output_price: 6 - supports_function_calling: true - - name: qwen/qwen3.5-plus-02-15 - max_input_tokens: 1000000 - max_output_tokens: 8192 - input_price: 0.4 - output_price: 2.4 - supports_function_calling: true - - name: qwen/qwen3.5-397b-a17b - max_input_tokens: 262144 - max_output_tokens: 8192 - input_price: 0.15 - output_price: 1 - supports_function_calling: true - - name: qwen/qwen3-next-80b-a3b-instruct - max_input_tokens: 262144 - input_price: 0.1 - output_price: 0.8 - supports_function_calling: true - - name: qwen/qwen3-next-80b-a3b-thinking - max_input_tokens: 262144 - input_price: 0.1 - output_price: 0.8 - - name: qwen/qwen3-235b-a22b-2507 # Qwen3 235B A22B Instruct 2507 - max_input_tokens: 262144 - input_price: 0.12 - output_price: 0.59 - supports_function_calling: true - - name: qwen/qwen3-235b-a22b-thinking-2507 - max_input_tokens: 262144 - input_price: 0.118 - output_price: 0.118 - - name: qwen/qwen3-30b-a3b-instruct-2507 - max_input_tokens: 131072 - input_price: 0.2 - output_price: 0.8 - - name: qwen/qwen3-30b-a3b-thinking-2507 - max_input_tokens: 262144 - input_price: 0.071 - output_price: 0.285 - - name: qwen/qwen3-vl-32b-instruct - max_input_tokens: 262144 - input_price: 0.35 - output_price: 1.1 - supports_vision: true - - name: qwen/qwen3-vl-8b-instruct - max_input_tokens: 262144 - input_price: 0.08 - output_price: 0.50 - supports_vision: true - - name: qwen/qwen3-coder-next - max_input_tokens: 262144 - input_price: 0.12 - output_price: 0.75 - supports_function_calling: true - - name: qwen/qwen3-coder-plus - max_input_tokens: 128000 - input_price: 1 - output_price: 5 - supports_function_calling: true - - name: qwen/qwen3-coder-flash - max_input_tokens: 128000 - input_price: 0.3 - output_price: 1.5 - supports_function_calling: true - - name: qwen/qwen3-coder # Qwen3 Coder 480B A35B - max_input_tokens: 262144 - input_price: 0.22 - output_price: 0.95 - supports_function_calling: true - - name: qwen/qwen3-coder-30b-a3b-instruct - max_input_tokens: 262144 - input_price: 0.052 - output_price: 0.207 - supports_function_calling: true - - name: moonshotai/kimi-k2.5 - max_input_tokens: 262144 - input_price: 0.57 - output_price: 2.85 - supports_vision: true - supports_function_calling: true - - name: moonshotai/kimi-k2-0905 - max_input_tokens: 262144 - input_price: 0.296 - output_price: 1.185 - supports_vision: true - supports_function_calling: true - - name: moonshotai/kimi-k2-thinking - max_input_tokens: 262144 - input_price: 0.45 - output_price: 2.35 - supports_function_calling: true - - name: x-ai/grok-4.1-fast - max_input_tokens: 2000000 - input_price: 0.2 - output_price: 0.5 - supports_function_calling: true - - name: x-ai/grok-code-fast-1 - max_input_tokens: 256000 - input_price: 0.2 - output_price: 1.5 - supports_function_calling: true - - name: amazon/nova-premier-v1 - max_input_tokens: 1000000 - input_price: 2.5 - output_price: 12.5 - supports_vision: true - - name: amazon/nova-pro-v1 - max_input_tokens: 300000 - max_output_tokens: 5120 - input_price: 0.8 - output_price: 3.2 - supports_vision: true - - name: amazon/nova-lite-v1 - max_input_tokens: 300000 - max_output_tokens: 5120 - input_price: 0.06 - output_price: 0.24 - supports_vision: true - - name: amazon/nova-micro-v1 - max_input_tokens: 128000 - max_output_tokens: 5120 - input_price: 0.035 - output_price: 0.14 - - name: perplexity/sonar-pro - max_input_tokens: 200000 - input_price: 3 - output_price: 15 - - name: perplexity/sonar - max_input_tokens: 127072 - input_price: 1 - output_price: 1 - - name: perplexity/sonar-reasoning-pro - max_input_tokens: 128000 - input_price: 2 - output_price: 8 - patch: - body: - include_reasoning: true - - name: perplexity/sonar-deep-research - max_input_tokens: 200000 - input_price: 2 - output_price: 8 - patch: - body: - include_reasoning: true - - name: minimax/minimax-m2.5 - max_input_tokens: 196608 - input_price: 0.3 - output_price: 1.1 - supports_function_calling: true - - name: minimax/minimax-m2.1 - max_input_tokens: 196608 - input_price: 0.12 - output_price: 0.48 - supports_function_calling: true - - name: z-ai/glm-5 - max_input_tokens: 204800 - input_price: 0.95 - output_price: 2.55 - supports_function_calling: true - - name: z-ai/glm-4.7 - max_input_tokens: 202752 - input_price: 0.16 - output_price: 0.80 - supports_function_calling: true - - name: z-ai/glm-4.7-flash - max_input_tokens: 202752 - input_price: 0.07 - output_price: 0.40 - supports_function_calling: true - - name: z-ai/glm-4.6v - max_input_tokens: 131072 - input_price: 0.3 - output_price: 0.9 - supports_vision: true - -# Links: -# - https://github.com/marketplace?type=models + - name: google/gemini-3-pro-preview + type: chat + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + default_reasoning_effort: high + - name: google/gemini-2.0-flash-001 + type: chat + max_input_tokens: 1000000 + input_price: 0.15 + output_price: 0.6 + supports_vision: true + supports_function_calling: true + - name: google/gemini-2.0-flash-lite-001 + type: chat + max_input_tokens: 1048576 + input_price: 0.075 + output_price: 0.3 + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-fable-5-1 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic/claude-opus-4-8 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic/claude-opus-4-7 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: mistralai/devstral-small + type: chat + max_input_tokens: 131072 + input_price: 0.07 + output_price: 0.28 + supports_function_calling: true + - name: ai21/jamba-large-1.7 + type: chat + max_input_tokens: 256000 + input_price: 2.0 + output_price: 8.0 + supports_function_calling: true + - name: x-ai/grok-4.1-fast + type: chat + max_input_tokens: 2000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true + - name: x-ai/grok-code-fast-1 + type: chat + max_input_tokens: 256000 + input_price: 0.2 + output_price: 1.5 + supports_function_calling: true + - name: aion-labs/aion-2.0 + type: chat + max_input_tokens: 131072 + input_price: 0.8 + output_price: 1.6 + max_output_tokens: 32768 + supports_function_calling: true + - name: aion-labs/aion-3.0 + type: chat + max_input_tokens: 131072 + input_price: 3.0 + output_price: 6.0 + max_output_tokens: 32768 + supports_function_calling: true + - name: aion-labs/aion-3.0-mini + type: chat + max_input_tokens: 131072 + input_price: 0.7 + output_price: 1.4 + max_output_tokens: 32768 + supports_function_calling: true + - name: aion-labs/aion-rp-llama-3.1-8b + type: chat + max_input_tokens: 32768 + input_price: 0.8 + output_price: 1.6 + max_output_tokens: 29491 + - name: amazon/nova-2-lite-v1 + type: chat + max_input_tokens: 1000000 + input_price: 0.3 + output_price: 2.5 + max_output_tokens: 65535 + supports_vision: true + supports_function_calling: true + - name: amazon/nova-lite-v1 + type: chat + max_input_tokens: 300000 + input_price: 0.06 + output_price: 0.24 + max_output_tokens: 5120 + supports_vision: true + supports_function_calling: true + - name: amazon/nova-micro-v1 + type: chat + max_input_tokens: 128000 + input_price: 0.035 + output_price: 0.14 + max_output_tokens: 5120 + supports_function_calling: true + - name: amazon/nova-premier-v1 + type: chat + max_input_tokens: 1000000 + input_price: 2.5 + output_price: 12.5 + max_output_tokens: 32000 + supports_vision: true + supports_function_calling: true + - name: amazon/nova-pro-v1 + type: chat + max_input_tokens: 300000 + input_price: 0.8 + output_price: 3.2 + max_output_tokens: 5120 + supports_vision: true + supports_function_calling: true + - name: anthracite-org/magnum-v4-72b + type: chat + max_input_tokens: 32768 + input_price: 2.5 + output_price: 5.0 + max_output_tokens: 4096 + - name: anthropic/claude-3-haiku + type: chat + max_input_tokens: 200000 + input_price: 0.25 + output_price: 1.25 + max_output_tokens: 4096 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-fable-5 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic/claude-fable-5.1 + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic/claude-fable-5.1:batch + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic/claude-fable-5:batch + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic/claude-haiku-4.5 + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-haiku-4.5:batch + type: chat + max_input_tokens: 200000 + input_price: 0.5 + output_price: 2.5 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + max_output_tokens: 32000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4.1 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 75.0 + max_output_tokens: 32000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4.1:batch + type: chat + max_input_tokens: 200000 + input_price: 7.5 + output_price: 37.5 + max_output_tokens: 32000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4.5 + type: chat + max_input_tokens: 200000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4.5:batch + type: chat + max_input_tokens: 200000 + input_price: 2.5 + output_price: 12.5 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4.6 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + default_reasoning_effort: high + - name: anthropic/claude-opus-4.6:batch + type: chat + max_input_tokens: 1000000 + input_price: 2.5 + output_price: 12.5 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4.7 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4.7:batch + type: chat + max_input_tokens: 1000000 + input_price: 2.5 + output_price: 12.5 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4.8 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-4.8:batch + type: chat + max_input_tokens: 1000000 + input_price: 2.5 + output_price: 12.5 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-opus-5 + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic/claude-opus-5:batch + type: chat + max_input_tokens: 1000000 + input_price: 2.5 + output_price: 12.5 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-sonnet-4 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-sonnet-4.5 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-sonnet-4.5:batch + type: chat + max_input_tokens: 1000000 + input_price: 1.5 + output_price: 7.5 + max_output_tokens: 64000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-sonnet-4.6 + type: chat + max_input_tokens: 1000000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - max + default_reasoning_effort: high + - name: anthropic/claude-sonnet-4.6:batch + type: chat + max_input_tokens: 1000000 + input_price: 1.5 + output_price: 7.5 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-sonnet-5 + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: high + - name: anthropic/claude-sonnet-5:batch + type: chat + max_input_tokens: 1000000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 128000 + require_max_tokens: true + supports_vision: true + supports_function_calling: true + - name: arcee-ai/trinity-large-thinking + type: chat + max_input_tokens: 262144 + input_price: 0.25 + output_price: 0.8 + max_output_tokens: 80000 + supports_function_calling: true + - name: baidu/ernie-4.5-vl-424b-a47b + type: chat + max_input_tokens: 123000 + input_price: 0.42 + output_price: 1.25 + max_output_tokens: 16000 + supports_vision: true + - name: bytedance-seed/seed-1.6 + type: chat + max_input_tokens: 262144 + input_price: 0.25 + output_price: 2.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: bytedance-seed/seed-1.6-flash + type: chat + max_input_tokens: 262144 + input_price: 0.075 + output_price: 0.3 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: bytedance-seed/seed-2-1-turbo + type: chat + max_input_tokens: 262144 + input_price: 0.5 + output_price: 2.5 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: bytedance-seed/seed-2.0-code + type: chat + max_input_tokens: 262144 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: bytedance-seed/seed-2.0-lite + type: chat + max_input_tokens: 262144 + input_price: 0.25 + output_price: 2.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: bytedance-seed/seed-2.0-mini + type: chat + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.4 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: bytedance/ui-tars-1.5-7b + type: chat + max_input_tokens: 128000 + input_price: 0.1 + output_price: 0.2 + max_output_tokens: 2048 + supports_vision: true + - name: cognitivecomputations/dolphin-mistral-24b-venice-edition + type: chat + max_input_tokens: 128000 + input_price: 0.2 + output_price: 0.9 + max_output_tokens: 8192 + - name: cohere/command-a + type: chat + max_input_tokens: 256000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 8192 + - name: cohere/command-r-08-2024 + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 4000 + supports_function_calling: true + - name: cohere/command-r-plus-08-2024 + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 4000 + supports_function_calling: true + - name: cohere/command-r7b-12-2024 + type: chat + max_input_tokens: 128000 + input_price: 0.0375 + output_price: 0.15 + max_output_tokens: 4000 + - name: cohere/north-mini-code:free + type: chat + max_input_tokens: 256000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 64000 + supports_function_calling: true + - name: deepseek/deepseek-chat + type: chat + max_input_tokens: 163840 + input_price: 0.2574 + output_price: 1.0287 + max_output_tokens: 16000 + supports_function_calling: true + - name: deepseek/deepseek-chat-v3-0324 + type: chat + max_input_tokens: 163840 + input_price: 0.25 + output_price: 1.0 + max_output_tokens: 147456 + supports_function_calling: true + - name: deepseek/deepseek-chat-v3.1 + type: chat + max_input_tokens: 163840 + input_price: 0.25 + output_price: 0.95 + max_output_tokens: 32768 + supports_function_calling: true + - name: deepseek/deepseek-r1 + type: chat + max_input_tokens: 64000 + input_price: 0.7 + output_price: 2.5 + max_output_tokens: 16000 + supports_function_calling: true + - name: deepseek/deepseek-r1-0528 + type: chat + max_input_tokens: 163840 + input_price: 0.5 + output_price: 2.15 + max_output_tokens: 32768 + supports_function_calling: true + - name: deepseek/deepseek-r1-distill-llama-70b + type: chat + max_input_tokens: 8192 + input_price: 0.8 + output_price: 0.8 + max_output_tokens: 7372 + - name: deepseek/deepseek-v3.1-terminus + type: chat + max_input_tokens: 163840 + input_price: 0.27 + output_price: 1.0 + max_output_tokens: 32768 + supports_function_calling: true + - name: deepseek/deepseek-v3.2 + type: chat + max_input_tokens: 163840 + input_price: 0.269 + output_price: 0.4 + max_output_tokens: 65536 + supports_function_calling: true + - name: deepseek/deepseek-v3.2-exp + type: chat + max_input_tokens: 163840 + input_price: 0.27 + output_price: 0.41 + max_output_tokens: 65536 + supports_function_calling: true + - name: deepseek/deepseek-v4-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.0825 + output_price: 0.1649 + max_output_tokens: 384000 + supports_function_calling: true + - name: deepseek/deepseek-v4-flash-0731 + type: chat + max_input_tokens: 1310720 + input_price: 0.065 + output_price: 0.18 + max_output_tokens: 943718 + supports_function_calling: true + - name: deepseek/deepseek-v4-flash-0731:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.14 + output_price: 0.28 + max_output_tokens: 943718 + supports_function_calling: true + - name: deepseek/deepseek-v4-flash-vision-exp + type: chat + max_input_tokens: 1048576 + input_price: 0.22 + output_price: 0.66 + max_output_tokens: 384000 + supports_vision: true + supports_function_calling: true + - name: deepseek/deepseek-v4-pro + type: chat + max_input_tokens: 1048576 + input_price: 1.0308 + output_price: 2.0616 + max_output_tokens: 384000 + supports_function_calling: true + - name: deepseek/deepseek-v4-pro-0813 + type: chat + max_input_tokens: 1048576 + input_price: 0.66 + output_price: 1.98 + max_output_tokens: 384000 + supports_function_calling: true + - name: deepseek/deepseek-v4-pro-0813:batch + type: chat + max_input_tokens: 1048576 + input_price: 1.32 + output_price: 3.96 + max_output_tokens: 943718 + supports_function_calling: true + - name: dots-studio/dots-3-note-preview:free + type: chat + max_input_tokens: 512000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 460800 + supports_vision: true + supports_function_calling: true + - name: google/gemini-2.5-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 2.5 + max_output_tokens: 65535 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + default_reasoning_effort: low + - name: google/gemini-2.5-flash-image + type: chat + max_input_tokens: 32768 + input_price: 0.3 + output_price: 2.5 + max_output_tokens: 8192 + supports_vision: true + - name: google/gemini-2.5-flash-lite + type: chat + max_input_tokens: 1048576 + input_price: 0.1 + output_price: 0.4 + max_output_tokens: 65535 + supports_vision: true + supports_function_calling: true + - name: google/gemini-2.5-flash-lite:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.05 + output_price: 0.2 + max_output_tokens: 65535 + supports_vision: true + supports_function_calling: true + - name: google/gemini-2.5-flash:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.15 + output_price: 1.25 + max_output_tokens: 65535 + supports_vision: true + supports_function_calling: true + - name: google/gemini-2.5-pro + type: chat + max_input_tokens: 1048576 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + default_reasoning_effort: high + - name: google/gemini-2.5-pro-preview + type: chat + max_input_tokens: 1048576 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-2.5-pro-preview-05-06 + type: chat + max_input_tokens: 1048576 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 65535 + supports_vision: true + supports_function_calling: true + - name: google/gemini-2.5-pro:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.625 + output_price: 5.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3-flash-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: high + - name: google/gemini-3-flash-preview:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.25 + output_price: 1.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3-pro-image + type: chat + max_input_tokens: 131072 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3-pro-image-preview + type: chat + max_input_tokens: 65536 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 32768 + supports_vision: true + - name: google/gemini-3.1-flash-image + type: chat + max_input_tokens: 131072 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 32768 + supports_vision: true + - name: google/gemini-3.1-flash-image-preview + type: chat + max_input_tokens: 65536 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 58982 + supports_vision: true + - name: google/gemini-3.1-flash-lite + type: chat + max_input_tokens: 1048576 + input_price: 0.25 + output_price: 1.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: minimal + - name: google/gemini-3.1-flash-lite-image + type: chat + max_input_tokens: 65536 + input_price: 0.25 + output_price: 1.5 + max_output_tokens: 58982 + supports_vision: true + - name: google/gemini-3.1-flash-lite-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.25 + output_price: 1.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.1-flash-lite:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.125 + output_price: 0.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.1-pro-preview + type: chat + max_input_tokens: 1048576 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + default_reasoning_effort: high + - name: google/gemini-3.1-pro-preview-customtools + type: chat + max_input_tokens: 1048576 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.1-pro-preview:batch + type: chat + max_input_tokens: 1048576 + input_price: 1.0 + output_price: 6.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.5-flash + type: chat + max_input_tokens: 1048576 + input_price: 1.5 + output_price: 9.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: medium + - name: google/gemini-3.5-flash-lite + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 2.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.5-flash-lite:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.15 + output_price: 1.25 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.5-flash:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 4.5 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.6-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.6-flash:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.375 + output_price: 1.875 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.7-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.7-flash:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.375 + output_price: 1.875 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.8-flash + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemini-3.8-flash:batch + type: chat + max_input_tokens: 1048576 + input_price: 0.375 + output_price: 1.875 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: google/gemma-2-27b-it + type: chat + max_input_tokens: 8192 + input_price: 0.65 + output_price: 0.65 + max_output_tokens: 2048 + - name: google/gemma-3-12b-it + type: chat + max_input_tokens: 131072 + input_price: 0.05 + output_price: 0.15 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: google/gemma-3-27b-it + type: chat + max_input_tokens: 131072 + input_price: 0.08 + output_price: 0.45 + max_output_tokens: 117964 + supports_vision: true + supports_function_calling: true + - name: google/gemma-3-4b-it + type: chat + max_input_tokens: 131072 + input_price: 0.05 + output_price: 0.1 + max_output_tokens: 16384 + supports_vision: true + - name: google/gemma-4-26b-a4b-it + type: chat + max_input_tokens: 262144 + input_price: 0.07 + output_price: 0.34 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: google/gemma-4-26b-a4b-it:free + type: chat + max_input_tokens: 262144 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: google/gemma-4-31b-it + type: chat + max_input_tokens: 262144 + input_price: 0.09 + output_price: 0.34 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: google/gemma-4-31b-it:batch + type: chat + max_input_tokens: 262144 + input_price: 0.39 + output_price: 0.97 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: google/gemma-4-31b-it:free + type: chat + max_input_tokens: 262144 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: google/lyria-3-clip-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 65536 + supports_vision: true + - name: google/lyria-3-pro-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 65536 + supports_vision: true + - name: gryphe/mythomax-l2-13b + type: chat + max_input_tokens: 8192 + input_price: 0.06 + output_price: 0.06 + max_output_tokens: 3686 + - name: ibm-granite/granite-4.0-h-micro + type: chat + max_input_tokens: 131000 + input_price: 0.017 + output_price: 0.112 + max_output_tokens: 117900 + - name: ibm-granite/granite-4.1-8b + type: chat + max_input_tokens: 131072 + input_price: 0.05 + output_price: 0.1 + max_output_tokens: 117964 + supports_function_calling: true + - name: ibm-granite/granite-4.2-8b + type: chat + max_input_tokens: 131072 + input_price: 0.1 + output_price: 0.15 + max_output_tokens: 117964 + supports_function_calling: true + - name: inception/mercury-2 + type: chat + max_input_tokens: 128000 + input_price: 0.25 + output_price: 0.75 + max_output_tokens: 50000 + supports_function_calling: true + - name: inception/mercury-2.5-preview + type: chat + max_input_tokens: 260000 + input_price: 0.04 + output_price: 0.15 + max_output_tokens: 65536 + supports_function_calling: true + - name: inclusionai/ling-3.0-flash + type: chat + max_input_tokens: 262144 + input_price: 0.021 + output_price: 0.063 + max_output_tokens: 32768 + supports_function_calling: true + - name: inclusionai/ling-3.0-flash-fin:free + type: chat + max_input_tokens: 262144 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 32768 + supports_function_calling: true + - name: kwaipilot/kat-coder-pro-v2 + type: chat + max_input_tokens: 262144 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 144000 + supports_function_calling: true + - name: kwaipilot/kat-coder-pro-v2.5 + type: chat + max_input_tokens: 262144 + input_price: 0.74 + output_price: 2.96 + max_output_tokens: 235929 + supports_function_calling: true + - name: liquid/lfm-2.5-2.6b:free + type: chat + max_input_tokens: 65536 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 8192 + supports_function_calling: true + - name: mancer/weaver + type: chat + max_input_tokens: 8000 + input_price: 0.4 + output_price: 0.75 + max_output_tokens: 6000 + - name: meituan/longcat-2.0 + type: chat + max_input_tokens: 1048756 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 262144 + supports_function_calling: true + - name: meta-llama/llama-3.1-70b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.4 + output_price: 0.4 + max_output_tokens: 16384 + supports_function_calling: true + - name: meta-llama/llama-3.1-8b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.05 + output_price: 0.08 + max_output_tokens: 117964 + supports_function_calling: true + - name: meta-llama/llama-3.2-1b-instruct + type: chat + max_input_tokens: 60000 + input_price: 0.027 + output_price: 0.201 + max_output_tokens: 54000 + - name: meta-llama/llama-3.2-3b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.05 + output_price: 0.33 + max_output_tokens: 117964 + - name: meta-llama/llama-3.3-70b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.71 + output_price: 0.71 + max_output_tokens: 115200 + supports_function_calling: true + - name: meta-llama/llama-4-maverick + type: chat + max_input_tokens: 1048576 + input_price: 0.2 + output_price: 0.696 + max_output_tokens: 115200 + supports_vision: true + supports_function_calling: true + - name: meta-llama/llama-4-scout + type: chat + max_input_tokens: 1310720 + input_price: 0.1 + output_price: 0.3 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: meta-llama/llama-guard-4-12b + type: chat + max_input_tokens: 163840 + input_price: 0.18 + output_price: 0.18 + max_output_tokens: 16384 + supports_vision: true + - name: meta/muse-glimmer-30b + type: chat + max_input_tokens: 131072 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: meta/muse-glimmer-30b:batch + type: chat + max_input_tokens: 131072 + input_price: 0.35 + output_price: 1.5 + max_output_tokens: 117964 + supports_vision: true + supports_function_calling: true + - name: meta/muse-spark-1.1 + type: chat + max_input_tokens: 1048576 + input_price: 1.25 + output_price: 4.25 + max_output_tokens: 943718 + supports_vision: true + supports_function_calling: true + - name: meta/muse-spark-1.2 + type: chat + max_input_tokens: 1048576 + input_price: 1.25 + output_price: 4.25 + max_output_tokens: 943718 + supports_vision: true + supports_function_calling: true + - name: meta/muse-spark-1.2-contributor + type: chat + max_input_tokens: 1048576 + input_price: 0.1 + output_price: 0.2 + max_output_tokens: 943718 + supports_vision: true + supports_function_calling: true + - name: microsoft/phi-4 + type: chat + max_input_tokens: 16384 + input_price: 0.07 + output_price: 0.14 + max_output_tokens: 14745 + - name: microsoft/wizardlm-2-8x22b + type: chat + max_input_tokens: 65535 + input_price: 0.62 + output_price: 0.62 + max_output_tokens: 8000 + - name: minimax/minimax-01 + type: chat + max_input_tokens: 1000192 + input_price: 0.2 + output_price: 1.1 + max_output_tokens: 900172 + supports_vision: true + - name: minimax/minimax-m1 + type: chat + max_input_tokens: 1000000 + input_price: 0.55 + output_price: 2.2 + max_output_tokens: 40000 + supports_function_calling: true + - name: minimax/minimax-m2 + type: chat + max_input_tokens: 204800 + input_price: 0.255 + output_price: 1.02 + max_output_tokens: 131072 + supports_function_calling: true + - name: minimax/minimax-m2-her + type: chat + max_input_tokens: 65536 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 2048 + - name: minimax/minimax-m2.1 + type: chat + max_input_tokens: 204800 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: minimax/minimax-m2.5 + type: chat + max_input_tokens: 204800 + input_price: 0.27 + output_price: 1.08 + max_output_tokens: 128000 + supports_function_calling: true + - name: minimax/minimax-m2.7 + type: chat + max_input_tokens: 204800 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: minimax/minimax-m2.7:free + type: chat + max_input_tokens: 196608 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 176947 + supports_function_calling: true + - name: minimax/minimax-m3 + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 512000 + supports_vision: true + supports_function_calling: true + - name: minimax/minimax-m3:batch + type: chat + max_input_tokens: 524288 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 471859 + supports_vision: true + supports_function_calling: true + - name: minimax/minimax-m3:free + type: chat + max_input_tokens: 1048576 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 943718 + supports_vision: true + supports_function_calling: true + - name: mistralai/codestral-2508 + type: chat + max_input_tokens: 256000 + input_price: 0.3 + output_price: 0.9 + max_output_tokens: 204800 + supports_function_calling: true + - name: mistralai/devstral-2512 + type: chat + max_input_tokens: 262144 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 209715 + supports_function_calling: true + - name: mistralai/ministral-14b-2512 + type: chat + max_input_tokens: 262144 + input_price: 0.2 + output_price: 0.2 + max_output_tokens: 209715 + supports_vision: true + supports_function_calling: true + - name: mistralai/ministral-3b-2512 + type: chat + max_input_tokens: 131072 + input_price: 0.1 + output_price: 0.1 + max_output_tokens: 104857 + supports_vision: true + supports_function_calling: true + - name: mistralai/ministral-8b-2512 + type: chat + max_input_tokens: 262144 + input_price: 0.15 + output_price: 0.15 + max_output_tokens: 209715 + supports_vision: true + supports_function_calling: true + - name: mistralai/mistral-large + type: chat + max_input_tokens: 128000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 102400 + supports_function_calling: true + - name: mistralai/mistral-large-2407 + type: chat + max_input_tokens: 131072 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 104857 + supports_function_calling: true + - name: mistralai/mistral-large-2512 + type: chat + max_input_tokens: 262144 + input_price: 0.5 + output_price: 1.5 + max_output_tokens: 209715 + supports_vision: true + supports_function_calling: true + - name: mistralai/mistral-medium-3 + type: chat + max_input_tokens: 131072 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 104857 + supports_vision: true + supports_function_calling: true + - name: mistralai/mistral-medium-3-5 + type: chat + max_input_tokens: 262144 + input_price: 1.5 + output_price: 7.5 + max_output_tokens: 209715 + supports_vision: true + supports_function_calling: true + - name: mistralai/mistral-medium-3-5:batch + type: chat + max_input_tokens: 262144 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 209715 + supports_vision: true + supports_function_calling: true + - name: mistralai/mistral-medium-3.1 + type: chat + max_input_tokens: 131072 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 104857 + supports_vision: true + supports_function_calling: true + - name: mistralai/mistral-nemo + type: chat + max_input_tokens: 131072 + input_price: 0.019 + output_price: 0.03 + max_output_tokens: 16384 + supports_function_calling: true + - name: mistralai/mistral-saba + type: chat + max_input_tokens: 32768 + input_price: 0.2 + output_price: 0.6 + max_output_tokens: 26214 + supports_function_calling: true + - name: mistralai/mistral-small-24b-instruct-2501 + type: chat + max_input_tokens: 32768 + input_price: 0.05 + output_price: 0.08 + max_output_tokens: 16384 + - name: mistralai/mistral-small-2603 + type: chat + max_input_tokens: 262144 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 209715 + supports_vision: true + supports_function_calling: true + - name: mistralai/mistral-small-3.1-24b-instruct + type: chat + max_input_tokens: 128000 + input_price: 0.351 + output_price: 0.555 + max_output_tokens: 102400 + supports_vision: true + - name: mistralai/mistral-small-3.2-24b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.075 + output_price: 0.2 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: mistralai/mixtral-8x22b-instruct + type: chat + max_input_tokens: 65536 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 52428 + supports_function_calling: true + - name: mistralai/voxtral-small-24b-2507 + type: chat + max_input_tokens: 32768 + input_price: 0.1 + output_price: 0.3 + max_output_tokens: 26214 + supports_function_calling: true + - name: moonshotai/kimi-k2 + type: chat + max_input_tokens: 131072 + input_price: 0.57 + output_price: 2.3 + max_output_tokens: 100352 + supports_function_calling: true + - name: moonshotai/kimi-k2-0905 + type: chat + max_input_tokens: 262144 + input_price: 0.6 + output_price: 2.5 + max_output_tokens: 100352 + supports_function_calling: true + - name: moonshotai/kimi-k2-thinking + type: chat + max_input_tokens: 262144 + input_price: 0.6 + output_price: 2.5 + max_output_tokens: 100352 + supports_function_calling: true + - name: moonshotai/kimi-k2.5 + type: chat + max_input_tokens: 262144 + input_price: 0.45 + output_price: 2.25 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: moonshotai/kimi-k2.6 + type: chat + max_input_tokens: 262144 + input_price: 0.95 + output_price: 4.0 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: moonshotai/kimi-k2.7-code + type: chat + max_input_tokens: 262144 + input_price: 0.66 + output_price: 3.4 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: moonshotai/kimi-k3 + type: chat + max_input_tokens: 1048576 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 943718 + supports_vision: true + supports_function_calling: true + - name: moonshotai/kimi-k3:batch + type: chat + max_input_tokens: 1048576 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 943718 + supports_vision: true + supports_function_calling: true + - name: morph/morph-v3-fast + type: chat + max_input_tokens: 81920 + input_price: 0.8 + output_price: 1.2 + max_output_tokens: 38000 + - name: morph/morph-v3-large + type: chat + max_input_tokens: 262144 + input_price: 0.9 + output_price: 1.9 + max_output_tokens: 131072 + - name: nex-agi/nex-n2-mini + type: chat + max_input_tokens: 262144 + input_price: 0.025 + output_price: 0.1 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: nex-agi/nex-n2-pro + type: chat + max_input_tokens: 262144 + input_price: 0.25 + output_price: 1.0 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: nousresearch/hermes-3-llama-3.1-405b + type: chat + max_input_tokens: 131072 + input_price: 1.0 + output_price: 1.0 + max_output_tokens: 16384 + - name: nousresearch/hermes-3-llama-3.1-70b + type: chat + max_input_tokens: 131072 + input_price: 0.7 + output_price: 0.7 + max_output_tokens: 16384 + - name: nousresearch/hermes-4-405b + type: chat + max_input_tokens: 131072 + input_price: 1.0 + output_price: 3.0 + max_output_tokens: 117964 + - name: nousresearch/hermes-4-70b + type: chat + max_input_tokens: 131072 + input_price: 0.13 + output_price: 0.4 + max_output_tokens: 117964 + - name: nvidia/nemotron-3-nano-30b-a3b + type: chat + max_input_tokens: 262144 + input_price: 0.05 + output_price: 0.2 + max_output_tokens: 228000 + supports_function_calling: true + - name: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free + type: chat + max_input_tokens: 256000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: nvidia/nemotron-3-super-120b-a12b + type: chat + max_input_tokens: 1000000 + input_price: 0.085 + output_price: 0.4 + max_output_tokens: 16384 + supports_function_calling: true + - name: nvidia/nemotron-3-super-120b-a12b:free + type: chat + max_input_tokens: 262144 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 235929 + supports_function_calling: true + - name: nvidia/nemotron-3-ultra-550b-a55b + type: chat + max_input_tokens: 262144 + input_price: 0.625 + output_price: 3.125 + max_output_tokens: 32768 + supports_function_calling: true + - name: nvidia/nemotron-3-ultra-550b-a55b:batch + type: chat + max_input_tokens: 512288 + input_price: 0.6 + output_price: 3.6 + max_output_tokens: 461059 + supports_function_calling: true + - name: nvidia/nemotron-3-ultra-550b-a55b:free + type: chat + max_input_tokens: 1000000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 65536 + supports_function_calling: true + - name: nvidia/nemotron-3.5-content-safety:free + type: chat + max_input_tokens: 128000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 8192 + supports_vision: true + - name: nvidia/nemotron-3.5-lightning + type: chat + max_input_tokens: 262144 + input_price: 0.08 + output_price: 0.2 + max_output_tokens: 131072 + supports_function_calling: true + - name: nvidia/nemotron-3.5-lightning:free + type: chat + max_input_tokens: 1000000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 65536 + supports_function_calling: true + - name: openai/gpt-3.5-turbo + type: chat + max_input_tokens: 16385 + input_price: 0.5 + output_price: 1.5 + max_output_tokens: 4096 + supports_function_calling: true + - name: openai/gpt-3.5-turbo-0613 + type: chat + max_input_tokens: 4095 + input_price: 1.0 + output_price: 2.0 + max_output_tokens: 3685 + supports_function_calling: true + - name: openai/gpt-3.5-turbo-16k + type: chat + max_input_tokens: 16385 + input_price: 3.0 + output_price: 4.0 + max_output_tokens: 4096 + supports_function_calling: true + - name: openai/gpt-3.5-turbo-instruct + type: chat + max_input_tokens: 4095 + input_price: 1.5 + output_price: 2.0 + max_output_tokens: 3685 + - name: openai/gpt-3.5-turbo:batch + type: chat + max_input_tokens: 16385 + input_price: 0.25 + output_price: 0.75 + max_output_tokens: 4096 + supports_function_calling: true + - name: openai/gpt-4 + type: chat + max_input_tokens: 8191 + input_price: 30.0 + output_price: 60.0 + max_output_tokens: 4096 + supports_function_calling: true + - name: openai/gpt-4-turbo + type: chat + max_input_tokens: 128000 + input_price: 10.0 + output_price: 30.0 + max_output_tokens: 4096 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4-turbo-preview + type: chat + max_input_tokens: 128000 + input_price: 10.0 + output_price: 30.0 + max_output_tokens: 4096 + supports_function_calling: true + - name: openai/gpt-4-turbo:batch + type: chat + max_input_tokens: 128000 + input_price: 5.0 + output_price: 15.0 + max_output_tokens: 4096 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4.1 + type: chat + max_input_tokens: 1047576 + input_price: 2.0 + output_price: 8.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4.1-mini + type: chat + max_input_tokens: 1047576 + input_price: 0.4 + output_price: 1.6 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4.1-mini:batch + type: chat + max_input_tokens: 1047576 + input_price: 0.2 + output_price: 0.8 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4.1-nano + type: chat + max_input_tokens: 1047576 + input_price: 0.1 + output_price: 0.4 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4.1-nano:batch + type: chat + max_input_tokens: 1047576 + input_price: 0.05 + output_price: 0.2 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4.1:batch + type: chat + max_input_tokens: 1047576 + input_price: 1.0 + output_price: 4.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4o + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4o-2024-05-13 + type: chat + max_input_tokens: 128000 + input_price: 5.0 + output_price: 15.0 + max_output_tokens: 4096 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4o-2024-08-06 + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4o-2024-11-20 + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4o-mini + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4o-mini-2024-07-18 + type: chat + max_input_tokens: 128000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4o-mini:batch + type: chat + max_input_tokens: 128000 + input_price: 0.075 + output_price: 0.3 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-4o:batch + type: chat + max_input_tokens: 128000 + input_price: 1.25 + output_price: 5.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5 + type: chat + max_input_tokens: 400000 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - minimal + - low + - medium + - high + default_reasoning_effort: medium + - name: openai/gpt-5-image + type: chat + max_input_tokens: 400000 + input_price: 10.0 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + - name: openai/gpt-5-image-mini + type: chat + max_input_tokens: 400000 + input_price: 2.5 + output_price: 2.0 + max_output_tokens: 128000 + supports_vision: true + - name: openai/gpt-5-mini + type: chat + max_input_tokens: 400000 + input_price: 0.25 + output_price: 2.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5-mini:batch + type: chat + max_input_tokens: 400000 + input_price: 0.125 + output_price: 1.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5-nano + type: chat + max_input_tokens: 400000 + input_price: 0.05 + output_price: 0.4 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5-nano:batch + type: chat + max_input_tokens: 400000 + input_price: 0.025 + output_price: 0.2 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5-pro + type: chat + max_input_tokens: 400000 + input_price: 15.0 + output_price: 120.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5-pro:batch + type: chat + max_input_tokens: 400000 + input_price: 7.5 + output_price: 60.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.1 + type: chat + max_input_tokens: 400000 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.1-codex + type: chat + max_input_tokens: 400000 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.1-codex-max + type: chat + max_input_tokens: 400000 + input_price: 1.25 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.1-codex-mini + type: chat + max_input_tokens: 400000 + input_price: 0.25 + output_price: 2.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.1:batch + type: chat + max_input_tokens: 400000 + input_price: 0.625 + output_price: 5.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.2 + type: chat + max_input_tokens: 400000 + input_price: 1.75 + output_price: 14.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: none + - name: openai/gpt-5.2-chat + type: chat + max_input_tokens: 128000 + input_price: 1.75 + output_price: 14.0 + max_output_tokens: 32000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.2-codex + type: chat + max_input_tokens: 400000 + input_price: 1.75 + output_price: 14.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.2-pro + type: chat + max_input_tokens: 400000 + input_price: 21.0 + output_price: 168.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - medium + - high + - xhigh + default_reasoning_effort: medium + - name: openai/gpt-5.2-pro:batch + type: chat + max_input_tokens: 400000 + input_price: 10.5 + output_price: 84.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.2:batch + type: chat + max_input_tokens: 400000 + input_price: 0.875 + output_price: 7.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.3-codex + type: chat + max_input_tokens: 400000 + input_price: 1.75 + output_price: 14.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + default_reasoning_effort: medium + - name: openai/gpt-5.4 + type: chat + max_input_tokens: 1050000 + input_price: 2.5 + output_price: 15.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: none + - name: openai/gpt-5.4-image-2 + type: chat + max_input_tokens: 272000 + input_price: 8.0 + output_price: 15.0 + max_output_tokens: 128000 + supports_vision: true + - name: openai/gpt-5.4-mini + type: chat + max_input_tokens: 400000 + input_price: 0.75 + output_price: 4.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: none + - name: openai/gpt-5.4-mini:batch + type: chat + max_input_tokens: 400000 + input_price: 0.375 + output_price: 2.25 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.4-nano + type: chat + max_input_tokens: 400000 + input_price: 0.2 + output_price: 1.25 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: none + - name: openai/gpt-5.4-nano:batch + type: chat + max_input_tokens: 400000 + input_price: 0.1 + output_price: 0.625 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.4-pro + type: chat + max_input_tokens: 1050000 + input_price: 30.0 + output_price: 180.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - medium + - high + - xhigh + default_reasoning_effort: medium + - name: openai/gpt-5.4-pro:batch + type: chat + max_input_tokens: 1050000 + input_price: 15.0 + output_price: 90.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.4:batch + type: chat + max_input_tokens: 1050000 + input_price: 1.25 + output_price: 7.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.5 + type: chat + max_input_tokens: 1050000 + input_price: 5.0 + output_price: 30.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + default_reasoning_effort: medium + - name: openai/gpt-5.5-pro + type: chat + max_input_tokens: 1050000 + input_price: 30.0 + output_price: 180.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - medium + - high + - xhigh + default_reasoning_effort: high + - name: openai/gpt-5.5-pro:batch + type: chat + max_input_tokens: 1050000 + input_price: 15.0 + output_price: 90.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.5:batch + type: chat + max_input_tokens: 1050000 + input_price: 2.5 + output_price: 15.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-5.6-luna + type: chat + max_input_tokens: 1050000 + input_price: 0.2 + output_price: 1.2 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-luna-pro + type: chat + max_input_tokens: 1050000 + input_price: 0.2 + output_price: 1.2 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-luna-pro:batch + type: chat + max_input_tokens: 1050000 + input_price: 0.1 + output_price: 0.6 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-luna:batch + type: chat + max_input_tokens: 1050000 + input_price: 0.1 + output_price: 0.6 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-sol + type: chat + max_input_tokens: 1050000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-sol-pro + type: chat + max_input_tokens: 1050000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-sol-pro:batch + type: chat + max_input_tokens: 1050000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-sol:batch + type: chat + max_input_tokens: 1050000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-terra + type: chat + max_input_tokens: 1050000 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-terra-pro + type: chat + max_input_tokens: 1050000 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-terra-pro:batch + type: chat + max_input_tokens: 1050000 + input_price: 1.0 + output_price: 6.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5.6-terra:batch + type: chat + max_input_tokens: 1050000 + input_price: 1.0 + output_price: 6.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - xhigh + - max + default_reasoning_effort: medium + - name: openai/gpt-5:batch + type: chat + max_input_tokens: 400000 + input_price: 0.625 + output_price: 5.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-audio + type: chat + max_input_tokens: 128000 + input_price: 2.5 + output_price: 10.0 + max_output_tokens: 16384 + supports_function_calling: true + - name: openai/gpt-audio-mini + type: chat + max_input_tokens: 128000 + input_price: 0.6 + output_price: 2.4 + max_output_tokens: 16384 + supports_function_calling: true + - name: openai/gpt-chat-latest + type: chat + max_input_tokens: 400000 + input_price: 5.0 + output_price: 30.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: openai/gpt-oss-120b + type: chat + max_input_tokens: 131072 + input_price: 0.037 + output_price: 0.17 + max_output_tokens: 117964 + supports_function_calling: true + - name: openai/gpt-oss-120b:batch + type: chat + max_input_tokens: 131072 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 117964 + supports_function_calling: true + - name: openai/gpt-oss-20b + type: chat + max_input_tokens: 131072 + input_price: 0.03 + output_price: 0.13 + max_output_tokens: 117964 + supports_function_calling: true + - name: openai/gpt-oss-20b:batch + type: chat + max_input_tokens: 131072 + input_price: 0.05 + output_price: 0.2 + max_output_tokens: 117964 + - name: openai/gpt-oss-safeguard-20b + type: chat + max_input_tokens: 131072 + input_price: 0.075 + output_price: 0.3 + max_output_tokens: 65536 + supports_function_calling: true + - name: openai/o1 + type: chat + max_input_tokens: 200000 + input_price: 15.0 + output_price: 60.0 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + - name: openai/o1-pro + type: chat + max_input_tokens: 200000 + input_price: 150.0 + output_price: 600.0 + max_output_tokens: 100000 + supports_vision: true + - name: openai/o3 + type: chat + max_input_tokens: 200000 + input_price: 2.0 + output_price: 8.0 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + - name: openai/o3-mini + type: chat + max_input_tokens: 200000 + input_price: 1.1 + output_price: 4.4 + max_output_tokens: 100000 + supports_function_calling: true + - name: openai/o3-mini-high + type: chat + max_input_tokens: 200000 + input_price: 1.1 + output_price: 4.4 + max_output_tokens: 100000 + supports_function_calling: true + - name: openai/o3-mini:batch + type: chat + max_input_tokens: 200000 + input_price: 0.55 + output_price: 2.2 + max_output_tokens: 100000 + supports_function_calling: true + - name: openai/o3-pro + type: chat + max_input_tokens: 200000 + input_price: 20.0 + output_price: 80.0 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + - name: openai/o3:batch + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 4.0 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + - name: openai/o4-mini + type: chat + max_input_tokens: 200000 + input_price: 1.1 + output_price: 4.4 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + - name: openai/o4-mini-high + type: chat + max_input_tokens: 200000 + input_price: 1.1 + output_price: 4.4 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + - name: openai/o4-mini:batch + type: chat + max_input_tokens: 200000 + input_price: 0.55 + output_price: 2.2 + max_output_tokens: 100000 + supports_vision: true + supports_function_calling: true + - name: openrouter/auto + type: chat + max_input_tokens: 2000000 + supports_vision: true + supports_function_calling: true + - name: openrouter/auto-beta + type: chat + max_input_tokens: 2000000 + supports_vision: true + supports_function_calling: true + - name: openrouter/bodybuilder + type: chat + max_input_tokens: 128000 + - name: openrouter/free + type: chat + max_input_tokens: 200000 + input_price: 0.0 + output_price: 0.0 + supports_vision: true + supports_function_calling: true + - name: openrouter/fusion + type: chat + max_input_tokens: 1000000 + - name: openrouter/pareto-code + type: chat + max_input_tokens: 2000000 + - name: perceptron/perceptron-mk1 + type: chat + max_input_tokens: 32768 + input_price: 0.15 + output_price: 1.5 + max_output_tokens: 8192 + supports_vision: true + - name: perplexity/sonar + type: chat + max_input_tokens: 127072 + input_price: 1.0 + output_price: 1.0 + max_output_tokens: 114364 + supports_vision: true + - name: perplexity/sonar-deep-research + type: chat + max_input_tokens: 128000 + input_price: 2.0 + output_price: 8.0 + patch: + body: + include_reasoning: true + max_output_tokens: 115200 + - name: perplexity/sonar-pro + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 8000 + supports_vision: true + - name: perplexity/sonar-pro-search + type: chat + max_input_tokens: 200000 + input_price: 3.0 + output_price: 15.0 + max_output_tokens: 8000 + supports_vision: true + - name: perplexity/sonar-reasoning-pro + type: chat + max_input_tokens: 128000 + input_price: 2.0 + output_price: 8.0 + patch: + body: + include_reasoning: true + max_output_tokens: 115200 + supports_vision: true + - name: poolside/laguna-s-2.1 + type: chat + max_input_tokens: 1048576 + input_price: 0.09 + output_price: 0.18 + max_output_tokens: 131072 + supports_function_calling: true + - name: poolside/laguna-s-2.1:free + type: chat + max_input_tokens: 262144 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 32768 + supports_function_calling: true + - name: poolside/laguna-xs-2.1 + type: chat + max_input_tokens: 262144 + input_price: 0.06 + output_price: 0.12 + max_output_tokens: 32768 + supports_function_calling: true + - name: poolside/laguna-xs-2.1:free + type: chat + max_input_tokens: 262144 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 32768 + supports_function_calling: true + - name: qwen/qwen-2.5-72b-instruct + type: chat + max_input_tokens: 32768 + input_price: 0.36 + output_price: 0.4 + max_output_tokens: 16384 + supports_function_calling: true + - name: qwen/qwen-2.5-7b-instruct + type: chat + max_input_tokens: 32768 + input_price: 0.1 + output_price: 0.2 + max_output_tokens: 29491 + supports_function_calling: true + - name: qwen/qwen-2.5-coder-32b-instruct + type: chat + max_input_tokens: 32768 + input_price: 0.66 + output_price: 1.0 + max_output_tokens: 29491 + - name: qwen/qwen-plus + type: chat + max_input_tokens: 1000000 + input_price: 0.26 + output_price: 0.78 + max_output_tokens: 32768 + supports_function_calling: true + - name: qwen/qwen-plus-2025-07-28 + type: chat + max_input_tokens: 1000000 + input_price: 0.26 + output_price: 0.78 + max_output_tokens: 32768 + supports_function_calling: true + - name: qwen/qwen2.5-vl-72b-instruct + type: chat + max_input_tokens: 128000 + input_price: 0.25 + output_price: 0.75 + max_output_tokens: 28800 + supports_vision: true + - name: qwen/qwen3-14b + type: chat + max_input_tokens: 131072 + input_price: 0.12 + output_price: 0.24 + max_output_tokens: 16384 + supports_function_calling: true + - name: qwen/qwen3-235b-a22b + type: chat + max_input_tokens: 131072 + input_price: 0.455 + output_price: 1.82 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen/qwen3-235b-a22b-2507 + type: chat + max_input_tokens: 262144 + input_price: 0.0875 + output_price: 0.35 + max_output_tokens: 235929 + supports_function_calling: true + - name: qwen/qwen3-235b-a22b-thinking-2507 + type: chat + max_input_tokens: 131072 + input_price: 0.23 + output_price: 2.3 + max_output_tokens: 117964 + supports_function_calling: true + - name: qwen/qwen3-30b-a3b + type: chat + max_input_tokens: 131072 + input_price: 0.12 + output_price: 0.5 + max_output_tokens: 16384 + supports_function_calling: true + - name: qwen/qwen3-30b-a3b-instruct-2507 + type: chat + max_input_tokens: 262144 + input_price: 0.0482 + output_price: 0.1931 + max_output_tokens: 32000 + supports_function_calling: true + - name: qwen/qwen3-30b-a3b-thinking-2507 + type: chat + max_input_tokens: 81920 + input_price: 0.2 + output_price: 2.4 + max_output_tokens: 32768 + supports_function_calling: true + - name: qwen/qwen3-32b + type: chat + max_input_tokens: 131072 + input_price: 0.08 + output_price: 0.28 + max_output_tokens: 16384 + supports_function_calling: true + - name: qwen/qwen3-8b + type: chat + max_input_tokens: 131072 + input_price: 0.117 + output_price: 0.455 + max_output_tokens: 8192 + supports_function_calling: true + - name: qwen/qwen3-coder + type: chat + max_input_tokens: 262144 + input_price: 0.3 + output_price: 1.0 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen/qwen3-coder-30b-a3b-instruct + type: chat + max_input_tokens: 262144 + input_price: 0.07 + output_price: 0.28 + max_output_tokens: 235929 + supports_function_calling: true + - name: qwen/qwen3-coder-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.195 + output_price: 0.975 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen/qwen3-coder-next + type: chat + max_input_tokens: 262144 + input_price: 0.12 + output_price: 0.8 + max_output_tokens: 235929 + supports_function_calling: true + - name: qwen/qwen3-coder-plus + type: chat + max_input_tokens: 1000000 + input_price: 0.65 + output_price: 3.25 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen/qwen3-max + type: chat + max_input_tokens: 262144 + input_price: 0.78 + output_price: 3.9 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen/qwen3-max-thinking + type: chat + max_input_tokens: 262144 + input_price: 0.78 + output_price: 3.9 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen/qwen3-next-80b-a3b-instruct + type: chat + max_input_tokens: 262144 + input_price: 0.1 + output_price: 1.1 + max_output_tokens: 235929 + supports_function_calling: true + - name: qwen/qwen3-next-80b-a3b-thinking + type: chat + max_input_tokens: 262144 + input_price: 0.15 + output_price: 1.2 + max_output_tokens: 32768 + supports_function_calling: true + - name: qwen/qwen3-vl-235b-a22b-instruct + type: chat + max_input_tokens: 262144 + input_price: 0.21 + output_price: 1.9 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3-vl-235b-a22b-thinking + type: chat + max_input_tokens: 131072 + input_price: 0.4 + output_price: 4.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3-vl-30b-a3b-instruct + type: chat + max_input_tokens: 262144 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3-vl-30b-a3b-thinking + type: chat + max_input_tokens: 262144 + input_price: 0.2 + output_price: 2.4 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3-vl-32b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.104 + output_price: 0.416 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3-vl-8b-instruct + type: chat + max_input_tokens: 262144 + input_price: 0.117 + output_price: 0.455 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3-vl-8b-thinking + type: chat + max_input_tokens: 131072 + input_price: 0.18 + output_price: 2.1 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.5-122b-a10b + type: chat + max_input_tokens: 262144 + input_price: 0.29 + output_price: 2.4 + max_output_tokens: 81920 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.5-27b + type: chat + max_input_tokens: 262144 + input_price: 0.195 + output_price: 1.56 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.5-35b-a3b + type: chat + max_input_tokens: 262144 + input_price: 0.25 + output_price: 1.25 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.5-397b-a17b + type: chat + max_input_tokens: 262144 + input_price: 0.39 + output_price: 2.34 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.5-9b + type: chat + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.15 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.5-9b:batch + type: chat + max_input_tokens: 262144 + input_price: 0.17 + output_price: 0.25 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.5-flash-02-23 + type: chat + max_input_tokens: 1000000 + input_price: 0.065 + output_price: 0.26 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.5-plus-02-15 + type: chat + max_input_tokens: 1000000 + input_price: 0.26 + output_price: 1.56 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.5-plus-20260420 + type: chat + max_input_tokens: 1000000 + input_price: 0.3 + output_price: 1.8 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.6-27b + type: chat + max_input_tokens: 262144 + input_price: 0.6 + output_price: 3.6 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.6-35b-a3b + type: chat + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.9 + max_output_tokens: 235929 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.6-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.1875 + output_price: 1.125 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.6-max-preview + type: chat + max_input_tokens: 262144 + input_price: 1.027 + output_price: 6.162 + max_output_tokens: 65536 + supports_function_calling: true + - name: qwen/qwen3.6-plus + type: chat + max_input_tokens: 1000000 + input_price: 0.325 + output_price: 1.95 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.7-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.03 + output_price: 0.13 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.7-max + type: chat + max_input_tokens: 1000000 + input_price: 1.475 + output_price: 4.425 + max_output_tokens: 131072 + supports_function_calling: true + - name: qwen/qwen3.7-plus + type: chat + max_input_tokens: 1000000 + input_price: 0.32 + output_price: 1.28 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.8-2.4t-a95b + type: chat + max_input_tokens: 1048576 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 131072 + supports_function_calling: true + - name: qwen/qwen3.8-2.4t-a95b:batch + type: chat + max_input_tokens: 1010000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 909000 + supports_function_calling: true + - name: qwen/qwen3.8-27b + type: chat + max_input_tokens: 1000000 + input_price: 0.425 + output_price: 2.55 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.8-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.15 + output_price: 0.47 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: qwen/qwen3.8-max + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: rekaai/reka-edge + type: chat + max_input_tokens: 16384 + input_price: 0.1 + output_price: 0.1 + max_output_tokens: 14745 + supports_vision: true + supports_function_calling: true + - name: rekaai/reka-flash-3 + type: chat + max_input_tokens: 65536 + input_price: 0.1 + output_price: 0.2 + max_output_tokens: 58982 + - name: relace/relace-apply-3 + type: chat + max_input_tokens: 256000 + input_price: 0.85 + output_price: 1.25 + max_output_tokens: 128000 + - name: relace/relace-search + type: chat + max_input_tokens: 256000 + input_price: 1.0 + output_price: 3.0 + max_output_tokens: 128000 + supports_function_calling: true + - name: sakana/fugu-ultra + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 30.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: sakana/sakana-namazu + type: chat + max_input_tokens: 262144 + input_price: 0.95 + output_price: 4.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: sao10k/l3-lunaris-8b + type: chat + max_input_tokens: 8192 + input_price: 0.04 + output_price: 0.05 + max_output_tokens: 7372 + - name: sao10k/l3.1-euryale-70b + type: chat + max_input_tokens: 131072 + input_price: 0.85 + output_price: 0.85 + max_output_tokens: 16384 + supports_function_calling: true + - name: sao10k/l3.3-euryale-70b + type: chat + max_input_tokens: 131072 + input_price: 0.65 + output_price: 0.75 + max_output_tokens: 16384 + - name: stepfun/step-3.5-flash + type: chat + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.3 + max_output_tokens: 65536 + supports_function_calling: true + - name: stepfun/step-3.7-flash + type: chat + max_input_tokens: 262144 + input_price: 0.2 + output_price: 1.15 + max_output_tokens: 230400 + supports_vision: true + supports_function_calling: true + - name: tencent/hunyuan-a13b-instruct + type: chat + max_input_tokens: 131072 + input_price: 0.14 + output_price: 0.57 + max_output_tokens: 117964 + - name: tencent/hy-mt2-1.8b + type: chat + max_input_tokens: 8192 + input_price: 0.044 + output_price: 0.177 + max_output_tokens: 4096 + - name: tencent/hy-mt2-30b-a3b + type: chat + max_input_tokens: 8192 + input_price: 0.074 + output_price: 0.295 + max_output_tokens: 4096 + - name: tencent/hy-mt2-7b + type: chat + max_input_tokens: 8192 + input_price: 0.074 + output_price: 0.295 + max_output_tokens: 4096 + - name: tencent/hy3 + type: chat + max_input_tokens: 262144 + input_price: 0.0825 + output_price: 0.33 + max_output_tokens: 128000 + supports_function_calling: true + - name: tencent/hy3-preview + type: chat + max_input_tokens: 262144 + input_price: 0.18 + output_price: 0.6 + max_output_tokens: 235929 + supports_function_calling: true + - name: tencent/hy4-preview + type: chat + max_input_tokens: 1048576 + input_price: 0.834 + output_price: 2.501 + max_output_tokens: 64000 + supports_function_calling: true + - name: thedrummer/cydonia-24b-v4.1 + type: chat + max_input_tokens: 131072 + input_price: 0.3 + output_price: 0.5 + max_output_tokens: 117964 + - name: thedrummer/skyfall-36b-v2 + type: chat + max_input_tokens: 32768 + input_price: 0.55 + output_price: 0.8 + max_output_tokens: 29491 + - name: thedrummer/unslopnemo-12b + type: chat + max_input_tokens: 1024000 + input_price: 0.4 + output_price: 0.4 + max_output_tokens: 26214 + supports_function_calling: true + - name: thinkingmachines/inkling + type: chat + max_input_tokens: 1048576 + input_price: 1.0 + output_price: 4.05 + max_output_tokens: 471859 + supports_vision: true + supports_function_calling: true + - name: thinkingmachines/inkling-small + type: chat + max_input_tokens: 1048576 + input_price: 0.45 + output_price: 1.2 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: thinkingmachines/inkling-small:batch + type: chat + max_input_tokens: 524288 + input_price: 0.5 + output_price: 1.2 + max_output_tokens: 471859 + supports_vision: true + supports_function_calling: true + - name: thinkingmachines/inkling-small:free + type: chat + max_input_tokens: 1048576 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: thinkingmachines/inkling:batch + type: chat + max_input_tokens: 524288 + input_price: 1.0 + output_price: 4.05 + max_output_tokens: 471859 + supports_vision: true + supports_function_calling: true + - name: thinkingmachines/inkling:free + type: chat + max_input_tokens: 1048576 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: undi95/remm-slerp-l2-13b + type: chat + max_input_tokens: 6144 + input_price: 0.45 + output_price: 0.65 + max_output_tokens: 4096 + - name: upstage/solar-pro-3 + type: chat + max_input_tokens: 131072 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 117964 + supports_function_calling: true + - name: upstage/solar-pro4 + type: chat + max_input_tokens: 524288 + input_price: 0.03 + output_price: 0.12 + max_output_tokens: 131072 + supports_function_calling: true + - name: writer/palmyra-x5 + type: chat + max_input_tokens: 1040000 + input_price: 0.6 + output_price: 6.0 + max_output_tokens: 8192 + - name: x-ai/grok-4.20 + type: chat + max_input_tokens: 2000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 1800000 + supports_vision: true + supports_function_calling: true + - name: x-ai/grok-4.20-multi-agent + type: chat + max_input_tokens: 2000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 1800000 + supports_vision: true + - name: x-ai/grok-4.3 + type: chat + max_input_tokens: 1000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 900000 + supports_vision: true + supports_function_calling: true + - name: x-ai/grok-4.5 + type: chat + max_input_tokens: 500000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 450000 + supports_vision: true + supports_function_calling: true + - name: x-ai/grok-4.6 + type: chat + max_input_tokens: 500000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 450000 + supports_vision: true + supports_function_calling: true + - name: x-ai/grok-build-0.1 + type: chat + max_input_tokens: 256000 + input_price: 1.0 + output_price: 2.0 + max_output_tokens: 230400 + supports_vision: true + supports_function_calling: true + - name: xiaomi/mimo-v2.5 + type: chat + max_input_tokens: 1050000 + input_price: 0.14 + output_price: 0.28 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: xiaomi/mimo-v2.5-pro + type: chat + max_input_tokens: 1050000 + input_price: 0.435 + output_price: 0.87 + max_output_tokens: 131072 + supports_function_calling: true + - name: z-ai/glm-4.5 + type: chat + max_input_tokens: 131072 + input_price: 0.6 + output_price: 2.2 + max_output_tokens: 98304 + supports_function_calling: true + - name: z-ai/glm-4.5-air + type: chat + max_input_tokens: 131072 + input_price: 0.13 + output_price: 0.85 + max_output_tokens: 98304 + supports_function_calling: true + - name: z-ai/glm-4.5v + type: chat + max_input_tokens: 65536 + input_price: 0.6 + output_price: 1.8 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: z-ai/glm-4.6 + type: chat + max_input_tokens: 204800 + input_price: 0.43 + output_price: 1.75 + max_output_tokens: 16384 + supports_function_calling: true + - name: z-ai/glm-4.6v + type: chat + max_input_tokens: 131072 + input_price: 0.3 + output_price: 0.9 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: z-ai/glm-4.7 + type: chat + max_input_tokens: 204800 + input_price: 0.4 + output_price: 1.75 + max_output_tokens: 131072 + supports_function_calling: true + - name: z-ai/glm-4.7-flash + type: chat + max_input_tokens: 202752 + input_price: 0.06 + output_price: 0.4 + max_output_tokens: 16384 + supports_function_calling: true + - name: z-ai/glm-5 + type: chat + max_input_tokens: 204800 + input_price: 0.6 + output_price: 1.92 + max_output_tokens: 128000 + supports_function_calling: true + - name: z-ai/glm-5-turbo + type: chat + max_input_tokens: 202752 + input_price: 1.2 + output_price: 4.0 + max_output_tokens: 131072 + supports_function_calling: true + - name: z-ai/glm-5.1 + type: chat + max_input_tokens: 204800 + input_price: 0.966 + output_price: 3.036 + max_output_tokens: 128000 + supports_function_calling: true + - name: z-ai/glm-5.2 + type: chat + max_input_tokens: 1048576 + input_price: 0.966 + output_price: 3.036 + max_output_tokens: 131072 + supports_function_calling: true + - name: z-ai/glm-5.2:free + type: chat + max_input_tokens: 256000 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 230400 + supports_function_calling: true + - name: z-ai/glm-5.3 + type: chat + max_input_tokens: 1310720 + input_price: 1.4 + output_price: 4.4 + max_output_tokens: 131072 + supports_function_calling: true + - name: z-ai/glm-5.3-flash + type: chat + max_input_tokens: 1310720 + input_price: 0.075 + output_price: 0.25 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: z-ai/glm-5.3-flash:batch + type: chat + max_input_tokens: 1048575 + input_price: 0.15 + output_price: 0.5 + max_output_tokens: 943717 + supports_vision: true + supports_function_calling: true + - name: z-ai/glm-5v-turbo + type: chat + max_input_tokens: 202752 + input_price: 1.2 + output_price: 4.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: ~anthropic/claude-fable-latest + type: chat + max_input_tokens: 1000000 + input_price: 10.0 + output_price: 50.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: ~anthropic/claude-haiku-latest + type: chat + max_input_tokens: 200000 + input_price: 1.0 + output_price: 5.0 + max_output_tokens: 64000 + supports_vision: true + supports_function_calling: true + - name: ~anthropic/claude-opus-latest + type: chat + max_input_tokens: 1000000 + input_price: 5.0 + output_price: 25.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: ~anthropic/claude-sonnet-latest + type: chat + max_input_tokens: 1000000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: ~deepseek/deepseek-v4-flash-latest + type: chat + max_input_tokens: 1310720 + input_price: 0.05 + output_price: 0.16 + max_output_tokens: 393216 + supports_function_calling: true + - name: ~google/gemini-flash-latest + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 3.75 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: ~google/gemini-pro-latest + type: chat + max_input_tokens: 1048576 + input_price: 2.0 + output_price: 12.0 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: ~moonshotai/kimi-latest + type: chat + max_input_tokens: 1048576 + input_price: 2.55 + output_price: 12.75 + max_output_tokens: 943718 + supports_vision: true + supports_function_calling: true + - name: ~openai/gpt-latest + type: chat + max_input_tokens: 1050000 + input_price: 2.0 + output_price: 10.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: ~openai/gpt-mini-latest + type: chat + max_input_tokens: 400000 + input_price: 0.75 + output_price: 4.5 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: ~x-ai/grok-latest + type: chat + max_input_tokens: 500000 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 450000 + supports_vision: true + supports_function_calling: true + - name: ~z-ai/glm-flash-latest + type: chat + max_input_tokens: 1310720 + input_price: 0.075 + output_price: 0.25 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: ~z-ai/glm-latest + type: chat + max_input_tokens: 1310720 + input_price: 1.15 + output_price: 3.5 + max_output_tokens: 235929 + supports_function_calling: true - provider: github models: - - name: gpt-5 - max_input_tokens: 400000 - max_output_tokens: 128000 - supports_vision: true - supports_function_calling: true - - name: gpt-5-mini - max_input_tokens: 400000 - max_output_tokens: 128000 - supports_vision: true - supports_function_calling: true - - name: gpt-5-nano - max_input_tokens: 400000 - max_output_tokens: 128000 - supports_vision: true - supports_function_calling: true - - name: gpt-4.1 - max_input_tokens: 1047576 - max_output_tokens: 32768 - supports_vision: true - supports_function_calling: true - - name: gpt-4o - max_input_tokens: 128000 - max_output_tokens: 16384 - supports_function_calling: true - - name: text-embedding-3-large - type: embedding - max_tokens_per_chunk: 8191 - default_chunk_size: 2000 - max_batch_size: 100 - - name: text-embedding-3-small - type: embedding - max_tokens_per_chunk: 8191 - default_chunk_size: 2000 - max_batch_size: 100 - - name: llama-4-maverick-17b-128e-instruct-fp8 - max_input_tokens: 1048576 - supports_vision: true - - name: llama-4-scout-17b-16e-instruct - max_input_tokens: 327680 - supports_vision: true - - name: llama-3.3-70b-instruct - max_input_tokens: 131072 - - name: mistral-medium-2505 - max_input_tokens: 131072 - supports_function_calling: true - - name: mistral-small-2503 - max_input_tokens: 131072 - supports_function_calling: true - - name: codestral-2501 - max_input_tokens: 256000 - supports_function_calling: true - - name: cohere-embed-v3-english - type: embedding - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 96 - - name: cohere-embed-v3-multilingual - type: embedding - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 96 - - name: deepseek-r1-0528 - max_input_tokens: 163840 - - name: deepseek-v3-0324 - max_input_tokens: 163840 - - name: mai-ds-r1 - max_input_tokens: 163840 - - name: phi-4 - max_input_tokens: 16384 - - name: phi-4-mini-instruct - max_input_tokens: 131072 - - name: phi-4-reasoning - max_input_tokens: 33792 - - name: phi-4-mini-reasoning - max_input_tokens: 131072 - - name: grok-3 - max_input_tokens: 131072 - - name: grok-3-mini - max_input_tokens: 131072 - -# Links: -# - https://deepinfra.com/models -# - https://deepinfra.com/docs/openai_api + - name: gpt-5 + type: chat + max_input_tokens: 400000 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: gpt-5-mini + type: chat + max_input_tokens: 400000 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: gpt-5-nano + type: chat + max_input_tokens: 400000 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: gpt-4.1 + type: chat + max_input_tokens: 1047576 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: gpt-4o + type: chat + max_input_tokens: 128000 + max_output_tokens: 16384 + supports_function_calling: true + - name: text-embedding-3-large + type: embedding + max_tokens_per_chunk: 8191 + default_chunk_size: 2000 + max_batch_size: 100 + - name: text-embedding-3-small + type: embedding + max_tokens_per_chunk: 8191 + default_chunk_size: 2000 + max_batch_size: 100 + - name: llama-4-maverick-17b-128e-instruct-fp8 + type: chat + max_input_tokens: 1048576 + supports_vision: true + - name: llama-4-scout-17b-16e-instruct + type: chat + max_input_tokens: 327680 + supports_vision: true + - name: llama-3.3-70b-instruct + type: chat + max_input_tokens: 131072 + - name: mistral-medium-2505 + type: chat + max_input_tokens: 131072 + supports_function_calling: true + - name: mistral-small-2503 + type: chat + max_input_tokens: 131072 + supports_function_calling: true + - name: codestral-2501 + type: chat + max_input_tokens: 256000 + supports_function_calling: true + - name: cohere-embed-v3-english + type: embedding + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 96 + - name: cohere-embed-v3-multilingual + type: embedding + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 96 + - name: deepseek-r1-0528 + type: chat + max_input_tokens: 163840 + - name: deepseek-v3-0324 + type: chat + max_input_tokens: 163840 + - name: mai-ds-r1 + type: chat + max_input_tokens: 163840 + - name: phi-4 + type: chat + max_input_tokens: 16384 + - name: phi-4-mini-instruct + type: chat + max_input_tokens: 131072 + - name: phi-4-reasoning + type: chat + max_input_tokens: 33792 + - name: phi-4-mini-reasoning + type: chat + max_input_tokens: 131072 + - name: grok-3 + type: chat + max_input_tokens: 131072 + - name: grok-3-mini + type: chat + max_input_tokens: 131072 - provider: deepinfra models: - - name: openai/gpt-oss-120b - max_input_tokens: 131072 - input_price: 0.09 - output_price: 0.45 - supports_function_calling: true - - name: openai/gpt-oss-20b - max_input_tokens: 131072 - input_price: 0.04 - output_price: 0.16 - supports_function_calling: true - - name: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 - max_input_tokens: 1048576 - input_price: 0.18 - output_price: 0.6 - supports_vision: true - - name: meta-llama/Llama-4-Scout-17B-16E-Instruct - max_input_tokens: 327680 - input_price: 0.08 - output_price: 0.3 - supports_vision: true - - name: Qwen/Qwen3-Max - max_input_tokens: 262144 - input_price: 1.2 - output_price: 6 - supports_function_calling: true - - name: Qwen/Qwen3-Max-Thinking - max_input_tokens: 262144 - input_price: 1.2 - output_price: 6 - supports_function_calling: true - - name: Qwen/Qwen3-Next-80B-A3B-Instruct - max_input_tokens: 262144 - input_price: 0.14 - output_price: 1.4 - supports_function_calling: true - - name: Qwen/Qwen3-Next-80B-A3B-Thinking - max_input_tokens: 262144 - input_price: 0.14 - output_price: 1.4 - - name: Qwen/Qwen3-235B-A22B-Instruct-2507 - max_input_tokens: 131072 - input_price: 0.13 - output_price: 0.6 - supports_function_calling: true - - name: Qwen/Qwen3-235B-A22B-Thinking-2507 - max_input_tokens: 131072 - input_price: 0.13 - output_price: 0.6 - - name: Qwen/Qwen3-Coder-480B-A35B-Instruct - max_input_tokens: 131072 - input_price: 0.4 - output_price: 1.6 - supports_function_calling: true - - name: Qwen/Qwen3-Coder-30B-A3B-Instruct - max_input_tokens: 262144 - input_price: 0.07 - output_price: 0.27 - supports_function_calling: true - - name: Qwen/Qwen3-30B-A3B - max_input_tokens: 40960 - input_price: 0.1 - output_price: 0.3 - - name: Qwen/Qwen3-VL-8B-Instruct - max_input_tokens: 262144 - input_price: 0.18 - output_price: 0.69 - supports_vision: true - - name: deepseek-ai/DeepSeek-V3.2 - max_input_tokens: 163840 - input_price: 0.26 - output_price: 0.39 - supports_function_calling: true - - name: google/gemma-3-27b-it - max_input_tokens: 131072 - input_price: 0.1 - output_price: 0.2 - - name: mistralai/Mistral-Small-3.2-24B-Instruct-2506 - max_input_tokens: 32768 - input_price: 0.06 - output_price: 0.12 - - name: moonshotai/Kimi-K2.5 - max_input_tokens: 262144 - input_price: 0.5 - output_price: 2.8 - supports_function_calling: true - - name: moonshotai/Kimi-K2-Instruct-0905 - max_input_tokens: 262144 - input_price: 0.5 - output_price: 2.0 - supports_function_calling: true - - name: moonshotai/Kimi-K2-Thinking - max_input_tokens: 262144 - input_price: 0.55 - output_price: 2.5 - supports_function_calling: true - - name: MiniMaxAI/MiniMax-M2.5 - max_input_tokens: 196608 - input_price: 0.27 - output_price: 0.95 - supports_function_calling: true - - name: MiniMaxAI/MiniMax-M2.1 - max_input_tokens: 196608 - input_price: 0.27 - output_price: 0.95 - supports_function_calling: true - - name: zai-org/GLM-5 - max_input_tokens: 202752 - input_price: 0.8 - output_price: 2.56 - supports_function_calling: true - - name: zai-org/GLM-4.7 - max_input_tokens: 202752 - input_price: 0.43 - output_price: 1.75 - supports_function_calling: true - - name: zai-org/GLM-4.7-Flash - max_input_tokens: 202752 - input_price: 0.06 - output_price: 0.4 - supports_function_calling: true - - name: zai-org/GLM-4.6V - max_input_tokens: 131072 - input_price: 0.3 - output_price: 0.9 - supports_vision: true - - name: BAAI/bge-large-en-v1.5 - type: embedding - input_price: 0.01 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 100 - - name: BAAI/bge-m3 - type: embedding - input_price: 0.01 - max_tokens_per_chunk: 8192 - default_chunk_size: 2000 - max_batch_size: 100 - - name: intfloat/e5-large-v2 - type: embedding - input_price: 0.01 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 100 - - name: intfloat/multilingual-e5-large - type: embedding - input_price: 0.01 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 100 - - name: thenlper/gte-large - type: embedding - input_price: 0.01 - max_tokens_per_chunk: 512 - default_chunk_size: 1000 - max_batch_size: 100 - -# Links: -# - https://jina.ai/models -# - https://api.jina.ai/redoc + - name: BAAI/bge-large-en-v1.5 + type: embedding + input_price: 0.01 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 100 + - name: BAAI/bge-m3 + type: embedding + input_price: 0.01 + max_tokens_per_chunk: 8192 + default_chunk_size: 2000 + max_batch_size: 100 + - name: intfloat/e5-large-v2 + type: embedding + input_price: 0.01 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 100 + - name: intfloat/multilingual-e5-large + type: embedding + input_price: 0.01 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 100 + - name: thenlper/gte-large + type: embedding + input_price: 0.01 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 100 + - name: Qwen/Qwen3-Max-Thinking + type: chat + max_input_tokens: 262144 + input_price: 1.2 + output_price: 6.0 + supports_function_calling: true + - name: Qwen/Qwen3-Next-80B-A3B-Thinking + type: chat + max_input_tokens: 262144 + input_price: 0.14 + output_price: 1.4 + - name: Qwen/Qwen3-235B-A22B-Thinking-2507 + type: chat + max_input_tokens: 131072 + input_price: 0.13 + output_price: 0.6 + - name: Qwen/Qwen3-Coder-480B-A35B-Instruct + type: chat + max_input_tokens: 131072 + input_price: 0.4 + output_price: 1.6 + supports_function_calling: true + - name: Qwen/Qwen3-Coder-30B-A3B-Instruct + type: chat + max_input_tokens: 262144 + input_price: 0.07 + output_price: 0.27 + supports_function_calling: true + - name: Qwen/Qwen3-VL-8B-Instruct + type: chat + max_input_tokens: 262144 + input_price: 0.18 + output_price: 0.69 + supports_vision: true + - name: google/gemma-3-27b-it + type: chat + max_input_tokens: 131072 + input_price: 0.1 + output_price: 0.2 + - name: mistralai/Mistral-Small-3.2-24B-Instruct-2506 + type: chat + max_input_tokens: 32768 + input_price: 0.06 + output_price: 0.12 + - name: moonshotai/Kimi-K2-Instruct-0905 + type: chat + max_input_tokens: 262144 + input_price: 0.5 + output_price: 2.0 + supports_function_calling: true + - name: moonshotai/Kimi-K2-Thinking + type: chat + max_input_tokens: 262144 + input_price: 0.55 + output_price: 2.5 + supports_function_calling: true + - name: MiniMaxAI/MiniMax-M2.1 + type: chat + max_input_tokens: 196608 + input_price: 0.27 + output_price: 0.95 + supports_function_calling: true + - name: zai-org/GLM-4.6V + type: chat + max_input_tokens: 131072 + input_price: 0.3 + output_price: 0.9 + supports_vision: true + - name: zai-org/GLM-5.3-Flash + type: chat + max_input_tokens: 1048576 + input_price: 0.15 + output_price: 0.5 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + - max + - name: Qwen/Qwen3.8-27B + type: chat + max_input_tokens: 262144 + input_price: 0.4 + output_price: 3.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - medium + - xhigh + - name: zai-org/GLM-5.3 + type: chat + max_input_tokens: 1048576 + input_price: 1.2 + output_price: 4.0 + max_output_tokens: 131072 + supports_function_calling: true + reasoning_levels: + - low + - high + - max + - name: Qwen/Qwen3.8-2.4T-A95B + type: chat + max_input_tokens: 262144 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 131072 + supports_function_calling: true + reasoning_levels: + - low + - medium + - xhigh + - name: deepseek-ai/DeepSeek-V4-Pro-0813 + type: chat + max_input_tokens: 1048576 + input_price: 1.3 + output_price: 2.6 + max_output_tokens: 384000 + supports_function_calling: true + reasoning_levels: + - high + - max + - name: Qwen/Qwen3.8-Max + type: chat + max_input_tokens: 256000 + input_price: 1.65 + output_price: 4.951 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + - name: deepseek-ai/DeepSeek-V4-Flash-0731 + type: chat + max_input_tokens: 1048576 + input_price: 0.08 + output_price: 0.18 + max_output_tokens: 384000 + supports_function_calling: true + - name: thinkingmachines/Inkling-Small + type: chat + max_input_tokens: 524288 + input_price: 0.45 + output_price: 1.2 + max_output_tokens: 1048576 + supports_vision: true + supports_function_calling: true + - name: moonshotai/Kimi-K3 + type: chat + max_input_tokens: 1048576 + input_price: 2.85 + output_price: 14.25 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + - max + - name: thinkingmachines/Inkling + type: chat + max_input_tokens: 524288 + input_price: 0.95 + output_price: 4.05 + max_output_tokens: 1048576 + supports_vision: true + supports_function_calling: true + - name: tencent/Hy3 + type: chat + max_input_tokens: 262144 + input_price: 0.14 + output_price: 0.58 + max_output_tokens: 64000 + supports_function_calling: true + - name: zai-org/GLM-5.2 + type: chat + max_input_tokens: 1048576 + input_price: 0.75 + output_price: 2.4 + max_output_tokens: 32768 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - name: moonshotai/Kimi-K2.7-Code + type: chat + max_input_tokens: 262144 + input_price: 0.68 + output_price: 3.4 + max_output_tokens: 262144 + supports_vision: true + supports_function_calling: true + - name: MiniMaxAI/MiniMax-M3 + type: chat + max_input_tokens: 524288 + input_price: 0.28 + output_price: 1.1 + max_output_tokens: 512000 + supports_vision: true + supports_function_calling: true + - name: stepfun-ai/Step-3.7-Flash + type: chat + max_input_tokens: 262144 + input_price: 0.2 + output_price: 1.15 + max_output_tokens: 256000 + supports_vision: true + supports_function_calling: true + - name: Qwen/Qwen3.7-Max + type: chat + max_input_tokens: 256000 + input_price: 2.5 + output_price: 7.5 + max_output_tokens: 65536 + supports_function_calling: true + - name: nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning + type: chat + max_input_tokens: 262144 + input_price: 0.2 + output_price: 0.8 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: deepseek-ai/DeepSeek-V4-Flash + type: chat + max_input_tokens: 1048576 + input_price: 0.09 + output_price: 0.18 + max_output_tokens: 16384 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - name: deepseek-ai/DeepSeek-V4-Pro + type: chat + max_input_tokens: 1048576 + input_price: 1.3 + output_price: 2.6 + max_output_tokens: 16384 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - xhigh + - name: Qwen/Qwen3.6-27B + type: chat + max_input_tokens: 262144 + input_price: 0.32 + output_price: 3.2 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: XiaomiMiMo/MiMo-V2.5 + type: chat + max_input_tokens: 262144 + input_price: 0.4 + output_price: 2.0 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: XiaomiMiMo/MiMo-V2.5-Pro + type: chat + max_input_tokens: 1048576 + input_price: 1.0 + output_price: 3.0 + max_output_tokens: 16384 + supports_function_calling: true + - name: moonshotai/Kimi-K2.6 + type: chat + max_input_tokens: 262144 + input_price: 0.75 + output_price: 3.5 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: zai-org/GLM-5.1 + type: chat + max_input_tokens: 202752 + input_price: 1.05 + output_price: 3.5 + max_output_tokens: 16384 + supports_function_calling: true + - name: google/gemma-4-26B-A4B-it + type: chat + max_input_tokens: 262144 + input_price: 0.07 + output_price: 0.34 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: google/gemma-4-31B-it + type: chat + max_input_tokens: 262144 + input_price: 0.13 + output_price: 0.38 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: google/gemma-4-E4B-it + type: chat + max_input_tokens: 131072 + input_price: 0.02 + output_price: 0.1 + max_output_tokens: 8192 + supports_vision: true + supports_function_calling: true + - name: Qwen/Qwen3.6-35B-A3B + type: chat + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.95 + max_output_tokens: 81920 + supports_vision: true + supports_function_calling: true + - name: MiniMaxAI/MiniMax-M2.7 + type: chat + max_input_tokens: 196608 + input_price: 0.25 + output_price: 1.0 + max_output_tokens: 131072 + supports_function_calling: true + - name: Qwen/Qwen3.5-122B-A10B + type: chat + max_input_tokens: 262144 + input_price: 0.29 + output_price: 2.4 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: Qwen/Qwen3.5-27B + type: chat + max_input_tokens: 262144 + input_price: 0.26 + output_price: 2.6 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: Qwen/Qwen3.5-9B + type: chat + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.15 + max_output_tokens: 65536 + supports_vision: true + supports_function_calling: true + - name: ByteDance/Seed-2.0-code + type: chat + max_input_tokens: 256000 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - medium + - high + - name: ByteDance/Seed-2.0-mini + type: chat + max_input_tokens: 256000 + input_price: 0.1 + output_price: 0.4 + max_output_tokens: 32000 + supports_vision: true + supports_function_calling: true + - name: ByteDance/Seed-2.0-pro + type: chat + max_input_tokens: 256000 + input_price: 0.5 + output_price: 3.0 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: MiniMaxAI/MiniMax-M2.5 + type: chat + max_input_tokens: 196608 + input_price: 0.15 + output_price: 1.15 + max_output_tokens: 131072 + supports_function_calling: true + - name: zai-org/GLM-5 + type: chat + max_input_tokens: 202752 + input_price: 0.6 + output_price: 2.08 + max_output_tokens: 16384 + supports_function_calling: true + - name: Qwen/Qwen3.5-35B-A3B + type: chat + max_input_tokens: 262144 + input_price: 0.14 + output_price: 1.0 + max_output_tokens: 81920 + supports_vision: true + supports_function_calling: true + - name: Qwen/Qwen3.5-397B-A17B + type: chat + max_input_tokens: 262144 + input_price: 0.45 + output_price: 3.0 + max_output_tokens: 81920 + supports_vision: true + supports_function_calling: true + - name: moonshotai/Kimi-K2.5 + type: chat + max_input_tokens: 262144 + input_price: 0.45 + output_price: 2.25 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: zai-org/GLM-4.7-Flash + type: chat + max_input_tokens: 202752 + input_price: 0.06 + output_price: 0.4 + max_output_tokens: 16384 + supports_function_calling: true + - name: zai-org/GLM-4.7 + type: chat + max_input_tokens: 202752 + input_price: 0.4 + output_price: 1.75 + max_output_tokens: 16384 + supports_function_calling: true + - name: nvidia/Nemotron-3-Nano-30B-A3B + type: chat + max_input_tokens: 262144 + input_price: 0.05 + output_price: 0.2 + max_output_tokens: 262144 + supports_function_calling: true + - name: deepseek-ai/DeepSeek-V3.2 + type: chat + max_input_tokens: 163840 + input_price: 0.26 + output_price: 0.38 + max_output_tokens: 64000 + supports_function_calling: true + - name: zai-org/GLM-4.6 + type: chat + max_input_tokens: 202752 + input_price: 0.5 + output_price: 2.0 + max_output_tokens: 131072 + supports_function_calling: true + - name: Qwen/Qwen3-Max + type: chat + max_input_tokens: 256000 + input_price: 1.2 + output_price: 6.0 + max_output_tokens: 65536 + supports_function_calling: true + - name: Qwen/Qwen3-VL-235B-A22B-Instruct + type: chat + max_input_tokens: 262144 + input_price: 0.2 + output_price: 0.88 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: Qwen/Qwen3-Next-80B-A3B-Instruct + type: chat + max_input_tokens: 262144 + input_price: 0.09 + output_price: 1.1 + max_output_tokens: 32768 + supports_function_calling: true + - name: deepseek-ai/DeepSeek-V3.1 + type: chat + max_input_tokens: 163840 + input_price: 0.25 + output_price: 0.95 + max_output_tokens: 8192 + supports_function_calling: true + - name: openai/gpt-oss-120b + type: chat + max_input_tokens: 131072 + input_price: 0.037 + output_price: 0.17 + max_output_tokens: 16384 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: openai/gpt-oss-20b + type: chat + max_input_tokens: 131072 + input_price: 0.03 + output_price: 0.14 + max_output_tokens: 16384 + supports_function_calling: true + reasoning_levels: + - low + - medium + - high + - name: nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 + type: chat + max_input_tokens: 131072 + input_price: 0.4 + output_price: 0.4 + max_output_tokens: 131072 + supports_function_calling: true + - name: Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo + type: chat + max_input_tokens: 262144 + input_price: 0.3 + output_price: 1.0 + max_output_tokens: 66536 + supports_function_calling: true + - name: Qwen/Qwen3-235B-A22B-Instruct-2507 + type: chat + max_input_tokens: 262144 + input_price: 0.09 + output_price: 0.55 + max_output_tokens: 16384 + supports_function_calling: true + - name: deepseek-ai/DeepSeek-R1-0528 + type: chat + max_input_tokens: 163840 + input_price: 0.5 + output_price: 2.15 + max_output_tokens: 64000 + supports_function_calling: true + - name: Qwen/Qwen3-30B-A3B + type: chat + max_input_tokens: 40960 + input_price: 0.12 + output_price: 0.5 + max_output_tokens: 16384 + supports_function_calling: true + - name: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 + type: chat + max_input_tokens: 1048576 + input_price: 0.2 + output_price: 0.8 + max_output_tokens: 16384 + supports_vision: true + - name: meta-llama/Llama-4-Scout-17B-16E-Instruct + type: chat + max_input_tokens: 327680 + input_price: 0.1 + output_price: 0.3 + max_output_tokens: 16384 + supports_vision: true + supports_function_calling: true + - name: Qwen/Qwen3-32B + type: chat + max_input_tokens: 40960 + input_price: 0.08 + output_price: 0.28 + max_output_tokens: 16384 + supports_function_calling: true + - name: deepseek-ai/DeepSeek-V3-0324 + type: chat + max_input_tokens: 163840 + input_price: 0.24 + output_price: 0.9 + max_output_tokens: 163840 + supports_function_calling: true + - name: deepseek-ai/DeepSeek-V3 + type: chat + max_input_tokens: 163840 + input_price: 0.32 + output_price: 0.89 + max_output_tokens: 8192 + supports_function_calling: true + - name: meta-llama/Llama-3.3-70B-Instruct-Turbo + type: chat + max_input_tokens: 131072 + input_price: 0.1 + output_price: 0.32 + max_output_tokens: 16384 + supports_function_calling: true - provider: jina models: - - name: jina-embeddings-v3 - type: embedding - input_price: 0 - max_tokens_per_chunk: 8192 - default_chunk_size: 2000 - max_batch_size: 100 - - name: jina-clip-v2 - type: embedding - input_price: 0 - max_tokens_per_chunk: 8192 - default_chunk_size: 1500 - max_batch_size: 100 - - name: jina-colbert-v2 - type: embedding - input_price: 0 - max_tokens_per_chunk: 8192 - default_chunk_size: 1500 - max_batch_size: 100 - - name: jina-reranker-v2-base-multilingual - type: reranker - max_input_tokens: 8192 - input_price: 0 - - name: jina-colbert-v2 - type: reranker - max_input_tokens: 8192 - input_price: 0 - -# Links: -# - https://docs.voyageai.com/docs/embeddings -# - https://docs.voyageai.com/docs/pricing -# - https://docs.voyageai.com/reference/ + - name: jina-embeddings-v3 + type: embedding + input_price: 0.0 + max_tokens_per_chunk: 8192 + default_chunk_size: 2000 + max_batch_size: 100 + - name: jina-clip-v2 + type: embedding + input_price: 0.0 + max_tokens_per_chunk: 8192 + default_chunk_size: 1500 + max_batch_size: 100 + - name: jina-colbert-v2 + type: embedding + input_price: 0.0 + max_tokens_per_chunk: 8192 + default_chunk_size: 1500 + max_batch_size: 100 + - name: jina-reranker-v2-base-multilingual + type: reranker + max_input_tokens: 8192 + input_price: 0.0 + - name: jina-colbert-v2 + type: reranker + max_input_tokens: 8192 + input_price: 0.0 - provider: voyageai models: - - name: voyage-3-large - type: embedding - max_input_tokens: 120000 - input_price: 0.18 - max_tokens_per_chunk: 32000 - default_chunk_size: 2000 - max_batch_size: 128 - - name: voyage-3 - type: embedding - max_input_tokens: 320000 - input_price: 0.06 - max_tokens_per_chunk: 32000 - default_chunk_size: 2000 - max_batch_size: 128 - - name: voyage-3-lite - type: embedding - max_input_tokens: 1000000 - input_price: 0.02 - max_tokens_per_chunk: 32000 - default_chunk_size: 1000 - max_batch_size: 128 - - name: rerank-2 - type: reranker - max_input_tokens: 16000 - input_price: 0.05 - - name: rerank-2-lite - type: reranker - max_input_tokens: 8000 - input_price: 0.02 + - name: voyage-3-large + type: embedding + max_input_tokens: 120000 + input_price: 0.18 + max_tokens_per_chunk: 32000 + default_chunk_size: 2000 + max_batch_size: 128 + - name: voyage-3 + type: embedding + max_input_tokens: 320000 + input_price: 0.06 + max_tokens_per_chunk: 32000 + default_chunk_size: 2000 + max_batch_size: 128 + - name: voyage-3-lite + type: embedding + max_input_tokens: 1000000 + input_price: 0.02 + max_tokens_per_chunk: 32000 + default_chunk_size: 1000 + max_batch_size: 128 + - name: rerank-2 + type: reranker + max_input_tokens: 16000 + input_price: 0.05 + - name: rerank-2-lite + type: reranker + max_input_tokens: 8000 + input_price: 0.02 diff --git a/quirks.yaml b/quirks.yaml index 65b2653..75e68c0 100644 --- a/quirks.yaml +++ b/quirks.yaml @@ -9,6 +9,11 @@ # entries are grouped under a `# legacy — pruning candidates` comment. - provider: openai + exclude: + - "text-embedding-*" + - "gpt-image-*" + - "chatgpt-image-*" + - "gpt-realtime*" rules: - match: "gpt-5.6-*" default_reasoning_effort: medium @@ -118,8 +123,39 @@ max_tokens: null temperature: null top_p: null + - name: chat-latest + max_input_tokens: 400000 + max_output_tokens: 128000 + input_price: 5 + output_price: 30 + supports_vision: true + supports_function_calling: true + - name: gpt-5.1-chat-latest + max_input_tokens: 400000 + max_output_tokens: 128000 + input_price: 1.25 + output_price: 10 + supports_vision: true + supports_function_calling: true + reasoning_levels: [none, low, medium, high] + default_reasoning_effort: none + - name: gpt-5-chat-latest + max_input_tokens: 400000 + max_output_tokens: 128000 + input_price: 1.25 + output_price: 10 + supports_vision: true + supports_function_calling: true + reasoning_levels: [minimal, low, medium, high] + default_reasoning_effort: medium - provider: gemini + exclude: + - "gemini-embedding-*" + - "veo-*" + - "*-tts" + - "*-tts-preview" + - "*-image-preview" rules: - match: "gemini-3.6-flash" default_reasoning_effort: medium @@ -135,6 +171,7 @@ default_reasoning_effort: high - match: "gemini-2.5-pro" default_reasoning_effort: high + reasoning_levels: [low, medium, high] models: - name: text-embedding-004 type: embedding @@ -142,6 +179,18 @@ max_tokens_per_chunk: 2048 default_chunk_size: 1500 max_batch_size: 100 + # legacy — pruning candidates + - name: gemini-3-pro-preview + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true + reasoning_levels: [low, high] + default_reasoning_effort: high + - name: gemma-3-27b-it + max_input_tokens: 131072 + max_output_tokens: 8192 + input_price: 0 + output_price: 0 - provider: claude rules: @@ -246,8 +295,28 @@ thinking: type: enabled budget_tokens: 16000 + models: + # legacy — pruning candidates + - name: claude-opus-4-1-20250805 + max_input_tokens: 200000 + max_output_tokens: 8192 + require_max_tokens: true + input_price: 15 + output_price: 75 + supports_vision: true + supports_function_calling: true + - name: claude-opus-4-20250514 + max_input_tokens: 200000 + max_output_tokens: 8192 + require_max_tokens: true + input_price: 15 + output_price: 75 + supports_vision: true + supports_function_calling: true - provider: mistral + exclude: + - "voxtral-*" models: - name: mistral-embed type: embedding @@ -255,6 +324,21 @@ input_price: 0.1 max_tokens_per_chunk: 8092 default_chunk_size: 2000 + # legacy — pruning candidates + - name: magistral-small-latest + max_input_tokens: 131072 + input_price: 0.5 + output_price: 1.5 + - name: devstral-small-latest + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.3 + supports_function_calling: true + - name: ministral-14b-latest + max_input_tokens: 262144 + input_price: 0.2 + output_price: 0.2 + supports_function_calling: true - provider: ai21 models: @@ -300,6 +384,8 @@ max_input_tokens: 4096 - provider: xai + exclude: + - "grok-imagine-*" oauth: client_id: b1a00492-073a-47ea-816f-4c329264a828 authorize_url: https://auth.x.ai/oauth2/authorize @@ -337,8 +423,71 @@ output_price: 2.5 max_input_tokens: 1000000 supports_function_calling: true + - name: grok-4-1-fast-non-reasoning + max_input_tokens: 1000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true + - name: grok-4-1-fast-reasoning + max_input_tokens: 1000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true + - name: grok-code-fast-1 + max_input_tokens: 256000 + input_price: 0.2 + output_price: 1.5 + supports_function_calling: true + - name: grok-3 + max_input_tokens: 131072 + input_price: 3 + output_price: 15 + supports_function_calling: true + - name: grok-3-mini + max_input_tokens: 131072 + input_price: 0.3 + output_price: 0.5 + supports_function_calling: true + +- provider: perplexity + models: + # legacy — pruning candidates + - name: sonar-reasoning + max_input_tokens: 128000 + input_price: 1 + output_price: 5 + +- provider: groq + exclude: + - "whisper-*" + models: + # legacy — pruning candidates + - name: meta-llama/llama-4-maverick-17b-128e-instruct + max_input_tokens: 131072 + input_price: 0 + output_price: 0 + supports_vision: true + supports_function_calling: true + - name: meta-llama/llama-4-scout-17b-16e-instruct + max_input_tokens: 131072 + input_price: 0 + output_price: 0 + supports_vision: true + supports_function_calling: true + - name: moonshotai/kimi-k2-instruct-0905 + max_input_tokens: 262144 + input_price: 0 + output_price: 0 + supports_function_calling: true + - name: qwen/qwen3-32b + max_input_tokens: 131072 + input_price: 0 + output_price: 0 - provider: vertexai + exclude: + - "gemini-embedding-*" + - "*-tts" rules: - match: "claude-*" require_max_tokens: true @@ -354,8 +503,10 @@ default_reasoning_effort: high - match: "gemini-2.5-flash" default_reasoning_effort: medium + reasoning_levels: [low, medium, high] - match: "gemini-2.5-pro" default_reasoning_effort: high + reasoning_levels: [low, medium, high] - match: "claude-opus-5" default_reasoning_effort: high - match: "claude-fable-*" @@ -449,6 +600,109 @@ max_tokens_per_chunk: 2048 default_chunk_size: 1500 max_batch_size: 5 + # legacy — pruning candidates + - name: gemini-3-pro-preview + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true + reasoning_levels: [low, high] + default_reasoning_effort: high + - name: claude-opus-5 + max_input_tokens: 1000000 + max_output_tokens: 128000 + require_max_tokens: true + input_price: 5 + output_price: 25 + supports_function_calling: true + supports_vision: true + reasoning_levels: [low, medium, high, xhigh, max] + default_reasoning_effort: high + - name: claude-fable-5-1 + max_input_tokens: 1000000 + max_output_tokens: 128000 + require_max_tokens: true + input_price: 10 + output_price: 50 + supports_function_calling: true + supports_vision: true + reasoning_levels: [low, medium, high, xhigh, max] + default_reasoning_effort: high + - name: claude-fable-5 + max_input_tokens: 1000000 + max_output_tokens: 128000 + require_max_tokens: true + input_price: 10 + output_price: 50 + supports_function_calling: true + supports_vision: true + reasoning_levels: [low, medium, high, xhigh, max] + default_reasoning_effort: high + - name: claude-opus-4-8 + max_input_tokens: 1000000 + max_output_tokens: 128000 + require_max_tokens: true + input_price: 5 + output_price: 25 + supports_vision: true + supports_function_calling: true + reasoning_levels: [low, medium, high, xhigh, max] + default_reasoning_effort: high + - name: claude-opus-4-7 + max_input_tokens: 1000000 + max_output_tokens: 128000 + require_max_tokens: true + input_price: 5 + output_price: 25 + supports_vision: true + supports_function_calling: true + reasoning_levels: [low, medium, high, xhigh, max] + default_reasoning_effort: high + - name: claude-opus-4-6 + max_input_tokens: 200000 + max_output_tokens: 8192 + require_max_tokens: true + input_price: 5 + output_price: 25 + supports_vision: true + supports_function_calling: true + - name: claude-sonnet-5 + max_input_tokens: 1000000 + max_output_tokens: 128000 + require_max_tokens: true + input_price: 3 + output_price: 15 + supports_vision: true + supports_function_calling: true + reasoning_levels: [low, medium, high, xhigh, max] + default_reasoning_effort: high + - name: claude-sonnet-4-6 + max_input_tokens: 200000 + max_output_tokens: 8192 + require_max_tokens: true + input_price: 3 + output_price: 15 + supports_vision: true + supports_function_calling: true + reasoning_levels: [low, medium, high, max] + default_reasoning_effort: high + - name: claude-3-5-haiku@20241022 + max_input_tokens: 200000 + max_output_tokens: 8192 + require_max_tokens: true + input_price: 0.8 + output_price: 4 + supports_vision: true + supports_function_calling: true + - name: mistral-small-2503 + max_input_tokens: 32000 + input_price: 0.1 + output_price: 0.3 + supports_function_calling: true + - name: codestral-2501 + max_input_tokens: 256000 + input_price: 0.3 + output_price: 0.9 + supports_function_calling: true - provider: bedrock rules: @@ -559,6 +813,36 @@ max_tokens_per_chunk: 512 default_chunk_size: 1000 max_batch_size: 96 + # legacy — pruning candidates + - name: us.meta.llama3-3-70b-instruct-v1:0 + max_input_tokens: 131072 + max_output_tokens: 8192 + require_max_tokens: true + input_price: 0.72 + output_price: 0.72 + supports_function_calling: true + - name: us.amazon.nova-premier-v1:0 + max_input_tokens: 300000 + max_output_tokens: 5120 + input_price: 2.5 + output_price: 12.5 + - name: us.amazon.nova-pro-v1:0 + max_input_tokens: 300000 + max_output_tokens: 5120 + input_price: 0.8 + output_price: 3.2 + supports_vision: true + - name: us.amazon.nova-lite-v1:0 + max_input_tokens: 300000 + max_output_tokens: 5120 + input_price: 0.06 + output_price: 0.24 + supports_vision: true + - name: us.amazon.nova-micro-v1:0 + max_input_tokens: 128000 + max_output_tokens: 5120 + input_price: 0.035 + output_price: 0.14 - provider: cloudflare rules: @@ -571,6 +855,13 @@ max_tokens_per_chunk: 512 default_chunk_size: 1000 max_batch_size: 100 + # legacy — pruning candidates + - name: '@cf/google/gemma-3-12b-it' + max_input_tokens: 131072 + max_output_tokens: 2048 + require_max_tokens: true + input_price: 0 + output_price: 0 - provider: ernie models: @@ -609,6 +900,8 @@ input_price: 0.07 - provider: qianwen + exclude: + - "*-realtime" rules: - match: "qwen3.5-plus" patch: @@ -646,6 +939,40 @@ max_tokens_per_chunk: 8192 default_chunk_size: 2000 max_batch_size: 10 + # legacy — pruning candidates + - name: qwen3-vl-flash + max_input_tokens: 262144 + supports_vision: true + - name: qwen3-235b-a22b-instruct-2507 + max_input_tokens: 131072 + input_price: 0.28 + output_price: 1.12 + supports_function_calling: true + - name: qwen3-235b-a22b-thinking-2507 + max_input_tokens: 131072 + input_price: 0.28 + output_price: 2.8 + - name: qwen3-30b-a3b-instruct-2507 + max_input_tokens: 131072 + input_price: 0.105 + output_price: 0.42 + supports_function_calling: true + - name: qwen3-30b-a3b-thinking-2507 + max_input_tokens: 131072 + input_price: 0.105 + output_price: 1.05 + - name: qwen3-vl-32b-instruct + max_input_tokens: 131072 + input_price: 0.28 + output_price: 1.12 + supports_vision: true + - name: qwen3-vl-8b-instruct + max_input_tokens: 131072 + input_price: 0.07 + output_price: 0.28 + supports_vision: true + - name: qwen3-coder-next + max_input_tokens: 262144 - provider: hunyuan models: @@ -671,6 +998,21 @@ default_chunk_size: 1000 max_batch_size: 100 +- provider: deepseek + models: + # legacy — pruning candidates + - name: deepseek-chat + max_input_tokens: 64000 + max_output_tokens: 8192 + input_price: 0.56 + output_price: 1.68 + supports_function_calling: true + - name: deepseek-reasoner + max_input_tokens: 64000 + max_output_tokens: 32768 + input_price: 0.56 + output_price: 1.68 + - provider: zhipuai variants: - match: "glm-5" @@ -698,6 +1040,46 @@ type: reranker max_input_tokens: 4096 input_price: 0.112 + # legacy — pruning candidates + - name: glm-4.6v-flash + max_input_tokens: 65536 + input_price: 0 + output_price: 0 + supports_vision: true + +- provider: minimax + models: + # legacy — pruning candidates + - name: minimax-m3 + max_input_tokens: 1000000 + input_price: 4.2 + output_price: 16.8 + supports_function_calling: true + - name: minimax-m2.7 + max_input_tokens: 204800 + input_price: 0.294 + output_price: 1.176 + supports_function_calling: true + - name: minimax-m2.5 + max_input_tokens: 204800 + input_price: 0.294 + output_price: 1.176 + supports_function_calling: true + - name: minimax-m2.5-highspeed + max_input_tokens: 204800 + input_price: 0.588 + output_price: 2.352 + supports_function_calling: true + - name: minimax-m2.1 + max_input_tokens: 204800 + input_price: 0.294 + output_price: 1.176 + supports_function_calling: true + - name: minimax-m2.1-highspeed + max_input_tokens: 204800 + input_price: 0.588 + output_price: 2.352 + supports_function_calling: true - provider: openrouter rules: @@ -705,54 +1087,76 @@ require_max_tokens: true - match: "openai/gpt-5.6-*" default_reasoning_effort: medium + reasoning_levels: [none, low, medium, high, xhigh, max] - match: "openai/gpt-5.5" default_reasoning_effort: medium + reasoning_levels: [none, low, medium, high, xhigh] - match: "openai/gpt-5.5-pro" default_reasoning_effort: high + reasoning_levels: [medium, high, xhigh] - match: "openai/gpt-5.4" default_reasoning_effort: none + reasoning_levels: [none, low, medium, high, xhigh] - match: "openai/gpt-5.4-pro" default_reasoning_effort: medium + reasoning_levels: [medium, high, xhigh] - match: "openai/gpt-5.4-mini" default_reasoning_effort: none + reasoning_levels: [none, low, medium, high, xhigh] - match: "openai/gpt-5.4-nano" default_reasoning_effort: none + reasoning_levels: [none, low, medium, high, xhigh] - match: "openai/gpt-5.3-codex" default_reasoning_effort: medium + reasoning_levels: [low, medium, high, xhigh] - match: "openai/gpt-5.2" default_reasoning_effort: none + reasoning_levels: [none, low, medium, high, xhigh] - match: "openai/gpt-5.2-pro" default_reasoning_effort: medium + reasoning_levels: [medium, high, xhigh] - match: "openai/gpt-5" default_reasoning_effort: medium + reasoning_levels: [minimal, low, medium, high] - match: "google/gemini-3.5-flash" default_reasoning_effort: medium + reasoning_levels: [minimal, low, medium, high] - match: "google/gemini-3-flash-preview" default_reasoning_effort: high + reasoning_levels: [minimal, low, medium, high] - match: "google/gemini-3.1-flash-lite" default_reasoning_effort: minimal + reasoning_levels: [minimal, low, medium, high] - match: "google/gemini-3.1-pro-preview" default_reasoning_effort: high + reasoning_levels: [low, medium, high] - match: "google/gemini-3-pro-preview" default_reasoning_effort: high - match: "google/gemini-2.5-flash" default_reasoning_effort: low + reasoning_levels: [low, medium, high] - match: "google/gemini-2.5-pro" default_reasoning_effort: high + reasoning_levels: [low, medium, high] - match: "anthropic/claude-opus-5" default_reasoning_effort: high + reasoning_levels: [low, medium, high, xhigh, max] - match: "anthropic/claude-fable-*" default_reasoning_effort: high + reasoning_levels: [low, medium, high, xhigh, max] - match: "anthropic/claude-opus-4-8" default_reasoning_effort: high - match: "anthropic/claude-opus-4-7" default_reasoning_effort: high - match: "anthropic/claude-opus-4.6" default_reasoning_effort: high + reasoning_levels: [low, medium, high, max] - match: "anthropic/claude-sonnet-5" default_reasoning_effort: high + reasoning_levels: [low, medium, high, xhigh, max] - match: "anthropic/claude-sonnet-4.6" default_reasoning_effort: high + reasoning_levels: [low, medium, high, max] - match: "perplexity/sonar-reasoning-pro" patch: body: @@ -761,9 +1165,105 @@ patch: body: include_reasoning: true + models: + # legacy — pruning candidates + - name: google/gemini-3-pro-preview + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true + reasoning_levels: [low, high] + default_reasoning_effort: high + - name: google/gemini-2.0-flash-001 + max_input_tokens: 1000000 + input_price: 0.15 + output_price: 0.6 + supports_vision: true + supports_function_calling: true + - name: google/gemini-2.0-flash-lite-001 + max_input_tokens: 1048576 + input_price: 0.075 + output_price: 0.3 + supports_vision: true + supports_function_calling: true + - name: anthropic/claude-fable-5-1 + max_input_tokens: 1000000 + max_output_tokens: 128000 + require_max_tokens: true + input_price: 10 + output_price: 50 + supports_function_calling: true + supports_vision: true + reasoning_levels: [low, medium, high, xhigh, max] + default_reasoning_effort: high + - name: anthropic/claude-opus-4-8 + max_input_tokens: 1000000 + max_output_tokens: 128000 + require_max_tokens: true + input_price: 5 + output_price: 25 + supports_vision: true + supports_function_calling: true + reasoning_levels: [low, medium, high, xhigh, max] + default_reasoning_effort: high + - name: anthropic/claude-opus-4-7 + max_input_tokens: 1000000 + max_output_tokens: 128000 + require_max_tokens: true + input_price: 5 + output_price: 25 + supports_vision: true + supports_function_calling: true + reasoning_levels: [low, medium, high, xhigh, max] + default_reasoning_effort: high + - name: mistralai/devstral-small + max_input_tokens: 131072 + input_price: 0.07 + output_price: 0.28 + supports_function_calling: true + - name: ai21/jamba-large-1.7 + max_input_tokens: 256000 + input_price: 2 + output_price: 8 + supports_function_calling: true + - name: x-ai/grok-4.1-fast + max_input_tokens: 2000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true + - name: x-ai/grok-code-fast-1 + max_input_tokens: 256000 + input_price: 0.2 + output_price: 1.5 + supports_function_calling: true +# Fully hand-owned: upstream catalogs track GitHub Copilot ids, which do not +# match the GitHub Models API ids coyote uses. - provider: github models: + - name: gpt-5 + max_input_tokens: 400000 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: gpt-5-mini + max_input_tokens: 400000 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: gpt-5-nano + max_input_tokens: 400000 + max_output_tokens: 128000 + supports_vision: true + supports_function_calling: true + - name: gpt-4.1 + max_input_tokens: 1047576 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true + - name: gpt-4o + max_input_tokens: 128000 + max_output_tokens: 16384 + supports_function_calling: true - name: text-embedding-3-large type: embedding max_tokens_per_chunk: 8191 @@ -774,6 +1274,23 @@ max_tokens_per_chunk: 8191 default_chunk_size: 2000 max_batch_size: 100 + - name: llama-4-maverick-17b-128e-instruct-fp8 + max_input_tokens: 1048576 + supports_vision: true + - name: llama-4-scout-17b-16e-instruct + max_input_tokens: 327680 + supports_vision: true + - name: llama-3.3-70b-instruct + max_input_tokens: 131072 + - name: mistral-medium-2505 + max_input_tokens: 131072 + supports_function_calling: true + - name: mistral-small-2503 + max_input_tokens: 131072 + supports_function_calling: true + - name: codestral-2501 + max_input_tokens: 256000 + supports_function_calling: true - name: cohere-embed-v3-english type: embedding max_tokens_per_chunk: 512 @@ -784,6 +1301,24 @@ max_tokens_per_chunk: 512 default_chunk_size: 1000 max_batch_size: 96 + - name: deepseek-r1-0528 + max_input_tokens: 163840 + - name: deepseek-v3-0324 + max_input_tokens: 163840 + - name: mai-ds-r1 + max_input_tokens: 163840 + - name: phi-4 + max_input_tokens: 16384 + - name: phi-4-mini-instruct + max_input_tokens: 131072 + - name: phi-4-reasoning + max_input_tokens: 33792 + - name: phi-4-mini-reasoning + max_input_tokens: 131072 + - name: grok-3 + max_input_tokens: 131072 + - name: grok-3-mini + max_input_tokens: 131072 - provider: deepinfra models: @@ -817,6 +1352,63 @@ max_tokens_per_chunk: 512 default_chunk_size: 1000 max_batch_size: 100 + # legacy — pruning candidates + - name: Qwen/Qwen3-Max-Thinking + max_input_tokens: 262144 + input_price: 1.2 + output_price: 6 + supports_function_calling: true + - name: Qwen/Qwen3-Next-80B-A3B-Thinking + max_input_tokens: 262144 + input_price: 0.14 + output_price: 1.4 + - name: Qwen/Qwen3-235B-A22B-Thinking-2507 + max_input_tokens: 131072 + input_price: 0.13 + output_price: 0.6 + - name: Qwen/Qwen3-Coder-480B-A35B-Instruct + max_input_tokens: 131072 + input_price: 0.4 + output_price: 1.6 + supports_function_calling: true + - name: Qwen/Qwen3-Coder-30B-A3B-Instruct + max_input_tokens: 262144 + input_price: 0.07 + output_price: 0.27 + supports_function_calling: true + - name: Qwen/Qwen3-VL-8B-Instruct + max_input_tokens: 262144 + input_price: 0.18 + output_price: 0.69 + supports_vision: true + - name: google/gemma-3-27b-it + max_input_tokens: 131072 + input_price: 0.1 + output_price: 0.2 + - name: mistralai/Mistral-Small-3.2-24B-Instruct-2506 + max_input_tokens: 32768 + input_price: 0.06 + output_price: 0.12 + - name: moonshotai/Kimi-K2-Instruct-0905 + max_input_tokens: 262144 + input_price: 0.5 + output_price: 2.0 + supports_function_calling: true + - name: moonshotai/Kimi-K2-Thinking + max_input_tokens: 262144 + input_price: 0.55 + output_price: 2.5 + supports_function_calling: true + - name: MiniMaxAI/MiniMax-M2.1 + max_input_tokens: 196608 + input_price: 0.27 + output_price: 0.95 + supports_function_calling: true + - name: zai-org/GLM-4.6V + max_input_tokens: 131072 + input_price: 0.3 + output_price: 0.9 + supports_vision: true - provider: jina models: diff --git a/scripts/requirements.txt b/scripts/requirements.txt deleted file mode 100644 index 69a538b..0000000 --- a/scripts/requirements.txt +++ /dev/null @@ -1,2 +0,0 @@ -requests -ruamel.yaml diff --git a/scripts/update_models.py b/scripts/update_models.py deleted file mode 100644 index fab2014..0000000 --- a/scripts/update_models.py +++ /dev/null @@ -1,255 +0,0 @@ -import requests -import sys -import re -import json - -# Provider mapping from models.yaml to OpenRouter prefixes -PROVIDER_MAPPING = { - "openai": "openai", - "claude": "anthropic", - "gemini": "google", - "mistral": "mistralai", - "cohere": "cohere", - "perplexity": "perplexity", - "xai": "x-ai", - "openrouter": "openrouter", - "ai21": "ai21", - "deepseek": "deepseek", - "moonshot": "moonshotai", - "qianwen": "qwen", - "zhipuai": "zhipuai", - "minimax": "minimax", - "vertexai": "google", - "groq": "groq", - "bedrock": "amazon", - "hunyuan": "tencent", - "ernie": "baidu", - "github": "github", -} - -def fetch_openrouter_models(): - print("Fetching models from OpenRouter...") - try: - response = requests.get("https://openrouter.ai/api/v1/models") - response.raise_for_status() - data = response.json()["data"] - print(f"Fetched {len(data)} models.") - return data - except Exception as e: - print(f"Error fetching models: {e}") - sys.exit(1) - -def get_openrouter_model(models_data, provider_prefix, model_name, is_openrouter_provider=False): - if is_openrouter_provider: - # For openrouter provider, the model_name in yaml is usually the full ID - for model in models_data: - if model["id"] == model_name: - return model - return None - - expected_id = f"{provider_prefix}/{model_name}" - - # 1. Try exact match on ID - for model in models_data: - if model["id"] == expected_id: - return model - - # 2. Try match by suffix - for model in models_data: - if model["id"].split("/")[-1] == model_name: - if model["id"].startswith(f"{provider_prefix}/"): - return model - - return None - -def format_price(price_per_token): - if price_per_token is None: - return None - try: - price_per_1m = float(price_per_token) * 1_000_000 - if price_per_1m.is_integer(): - return str(int(price_per_1m)) - else: - return str(round(price_per_1m, 4)) - except: - return None - -def get_indentation(line): - return len(line) - len(line.lstrip()) - -def process_model_block(block_lines, current_provider, or_models): - if not block_lines: - return [] - - # 1. Identify model name and indentation - name_line = block_lines[0] - name_match = re.match(r"^(\s*)-\s*name:\s*(.+)$", name_line) - if not name_match: - return block_lines - - name_indent_str = name_match.group(1) - model_name = name_match.group(2).strip() - - # 2. Find OpenRouter model - or_prefix = PROVIDER_MAPPING.get(current_provider) - is_openrouter_provider = (current_provider == "openrouter") - - if not or_prefix and not is_openrouter_provider: - return block_lines - - or_model = get_openrouter_model(or_models, or_prefix, model_name, is_openrouter_provider) - if not or_model: - return block_lines - - print(f" Updating {model_name}...") - - # 3. Prepare updates - updates = {} - - # Pricing - pricing = or_model.get("pricing", {}) - p_in = format_price(pricing.get("prompt")) - p_out = format_price(pricing.get("completion")) - if p_in: updates["input_price"] = p_in - if p_out: updates["output_price"] = p_out - - # Context - ctx = or_model.get("context_length") - if ctx: updates["max_input_tokens"] = str(ctx) - - max_out = None - if "top_provider" in or_model and or_model["top_provider"]: - max_out = or_model["top_provider"].get("max_completion_tokens") - if max_out: updates["max_output_tokens"] = str(max_out) - - # Capabilities - arch = or_model.get("architecture", {}) - modality = arch.get("modality", "") - if "image" in modality: - updates["supports_vision"] = "true" - - # 4. Detect field indentation - field_indent_str = None - existing_fields = {} # key -> line_index - - for i, line in enumerate(block_lines): - if i == 0: continue # Skip name line - - # Skip comments - if line.strip().startswith("#"): - continue - - # Look for "key: value" - m = re.match(r"^(\s*)([\w_-]+):", line) - if m: - indent = m.group(1) - key = m.group(2) - # Must be deeper than name line - if len(indent) > len(name_indent_str): - if field_indent_str is None: - field_indent_str = indent - existing_fields[key] = i - - if field_indent_str is None: - field_indent_str = name_indent_str + " " - - # 5. Apply updates - new_block = list(block_lines) - - # Update existing fields - for key, value in updates.items(): - if key in existing_fields: - idx = existing_fields[key] - # Preserve original key indentation exactly - original_line = new_block[idx] - m = re.match(r"^(\s*)([\w_-]+):", original_line) - if m: - current_indent = m.group(1) - new_block[idx] = f"{current_indent}{key}: {value}\n" - - # Insert missing fields - # Insert after the name line - insertion_idx = 1 - - for key, value in updates.items(): - if key not in existing_fields: - new_line = f"{field_indent_str}{key}: {value}\n" - new_block.insert(insertion_idx, new_line) - insertion_idx += 1 - - return new_block - -def main(): - or_models = fetch_openrouter_models() - - print("Reading models.yaml...") - with open("models.yaml", "r") as f: - lines = f.readlines() - - new_lines = [] - current_provider = None - - i = 0 - while i < len(lines): - line = lines[i] - - # Check for provider - # - provider: name - p_match = re.match(r"^\s*-?\s*provider:\s*(.+)$", line) - if p_match: - current_provider = p_match.group(1).strip() - new_lines.append(line) - i += 1 - continue - - # Check for model start - # - name: ... - m_match = re.match(r"^(\s*)-\s*name:\s*.+$", line) - if m_match: - # Start of a model block - start_indent = len(m_match.group(1)) - - # Collect block lines - block_lines = [line] - j = i + 1 - while j < len(lines): - next_line = lines[j] - stripped = next_line.strip() - - # If empty or comment, include it - if not stripped or stripped.startswith("#"): - block_lines.append(next_line) - j += 1 - continue - - # Check indentation - next_indent = get_indentation(next_line) - - # If indentation is greater, it's part of the block (property) - if next_indent > start_indent: - block_lines.append(next_line) - j += 1 - continue - - # If indentation is equal or less, it's the end of the block - break - - # Process the block - processed_block = process_model_block(block_lines, current_provider, or_models) - new_lines.extend(processed_block) - - # Advance i - i = j - continue - - # Otherwise, just a regular line - new_lines.append(line) - i += 1 - - print("Saving models.yaml...") - with open("models.yaml", "w") as f: - f.writelines(new_lines) - print("Done.") - -if __name__ == "__main__": - main() diff --git a/src/cli/mod.rs b/src/cli/mod.rs index fbd3d92..f53658b 100644 --- a/src/cli/mod.rs +++ b/src/cli/mod.rs @@ -12,6 +12,7 @@ use clap_complete::ArgValueCompleter; use is_terminal::IsTerminal; use std::collections::HashSet; use std::io::{Read, stdin}; +use std::path::PathBuf; #[derive(clap::ValueEnum, Debug, Clone, Copy, PartialEq, Eq)] pub enum McpTransportArg { @@ -53,7 +54,7 @@ pub enum McpScopeArg { "install_builtins", "sync_models", "list_models", "list_roles", "list_sessions", "list_agents", "list_rags", "list_macros", "list_skills", "list_bundles", "skill", "tail_logs", "completions", - "update", "update_bundle", "uninstall", + "update", "update_bundle", "uninstall", "generate_models", ]) ), group( @@ -253,6 +254,15 @@ pub struct Cli { /// Sync models updates #[arg(long, help_heading = "Installation & Updates")] pub sync_models: bool, + /// Regenerate the models catalog file from live API data + #[arg( + long, + hide = true, + value_name = "PATH", + num_args = 0..=1, + default_missing_value = "models.yaml" + )] + pub generate_models: Option, /// Update Coyote to the latest release, or to a specific version #[arg(long, value_name = "VERSION", help_heading = "Installation & Updates")] pub update: Option>, @@ -810,6 +820,19 @@ mod tests { assert!(cli.sync_models); } + #[test] + fn parse_generate_models_flag() { + assert_eq!(parse(&[]).generate_models, None); + assert_eq!( + parse(&["--generate-models"]).generate_models, + Some(PathBuf::from("models.yaml")) + ); + assert_eq!( + parse(&["--generate-models", "out.yaml"]).generate_models, + Some(PathBuf::from("out.yaml")) + ); + } + #[test] fn parse_model_with_role() { let cli = parse(&["-m", "gpt-4o", "-r", "coder"]); diff --git a/src/client/catalog.rs b/src/client/catalog.rs index 4d18162..cec2d46 100644 --- a/src/client/catalog.rs +++ b/src/client/catalog.rs @@ -13,7 +13,6 @@ use std::sync::LazyLock; pub const QUIRKS_YAML: &str = include_str!("../../quirks.yaml"); -#[allow(dead_code)] pub static ALL_QUIRKS: LazyLock> = LazyLock::new(|| serde_yaml::from_str(QUIRKS_YAML).expect("quirks.yaml must be valid")); @@ -133,8 +132,8 @@ const PROVIDER_SOURCES: [SourceIds; 24] = [ }, SourceIds { provider: "github", - modelsdev: Some("github-copilot"), - openrouter: Some("github"), + modelsdev: None, + openrouter: None, }, SourceIds { provider: "deepinfra", @@ -162,7 +161,6 @@ pub struct FetchedSources { /// Fetches both upstream catalogs concurrently. A failed fetch is logged and /// surfaces as `None` rather than an error. -#[allow(dead_code)] pub async fn fetch_sources() -> FetchedSources { let (modelsdev, openrouter) = tokio::join!(fetch(MODELSDEV_API_URL), fetch(OPENROUTER_API_URL)); FetchedSources { @@ -478,7 +476,6 @@ pub fn build_catalog(sources: &FetchedSources, quirks: &[ProviderQuirks]) -> Cat /// Like [`build_catalog`], but errors unless every provider was assembled /// from live API data (or is quirks-owned by design). -#[allow(dead_code)] pub fn build_catalog_strict( sources: &FetchedSources, quirks: &[ProviderQuirks], @@ -494,6 +491,32 @@ pub fn build_catalog_strict( Ok(build.providers) } +const GENERATED_HEADER: &str = "# GENERATED by 'coyote --generate-models' — DO NOT hand-edit model data.\n\ +# Hand-owned behavior lives in quirks.yaml; this file is the embedded offline fallback.\n"; + +/// Builds the catalog from live API data and writes it to `path`. Both +/// upstream sources must respond and every provider must fully resolve; +/// identical source data always produces identical bytes. +pub async fn generate_models_file(path: &std::path::Path) -> Result<()> { + let sources = fetch_sources().await; + if sources.modelsdev.is_none() || sources.openrouter.is_none() { + bail!( + "generating the models file requires both catalog sources; see the log for the failed fetch" + ); + } + let providers = build_catalog_strict(&sources, &ALL_QUIRKS)?; + let model_count: usize = providers.iter().map(|provider| provider.models.len()).sum(); + let yaml = serde_yaml::to_string(&providers)?; + std::fs::write(path, format!("{GENERATED_HEADER}{yaml}"))?; + println!( + "Wrote {} models across {} providers to {}", + model_count, + providers.len(), + path.display() + ); + Ok(()) +} + /// Fraction of `old` names that also appear in `new`; empty `old` yields 1.0. /// Used to guard against upstream id-shape drift: a low overlap means the /// upstream catalog renamed its models out from under us. @@ -1333,6 +1356,8 @@ rules: models: [{name: e}] - provider: hunyuan models: [{name: h}] +- provider: github + models: [{name: g}] - provider: jina models: [{name: j}] - provider: voyageai @@ -1358,6 +1383,96 @@ rules: assert_eq!(name_overlap(&old, &[]), 0.0); } + fn embedded_catalog() -> Vec { + serde_yaml::from_str(crate::client::MODELS_YAML).unwrap() + } + + fn embedded_provider<'a>(providers: &'a [ProviderModels], name: &str) -> &'a ProviderModels { + providers + .iter() + .find(|provider| provider.provider == name) + .unwrap_or_else(|| panic!("provider '{name}' missing from models.yaml")) + } + + #[test] + fn embedded_catalog_invariants() { + let providers = embedded_catalog(); + assert!(providers.len() >= 24); + let order: Vec<&str> = providers + .iter() + .map(|provider| provider.provider.as_str()) + .collect(); + assert_eq!(order, KNOWN_PROVIDERS); + + assert!(embedded_provider(&providers, "xai").oauth.is_some()); + for name in ["jina", "voyageai"] { + assert!( + embedded_provider(&providers, name) + .models + .iter() + .any(|model| model.model_type == "embedding"), + "{name} lost its embedding models" + ); + } + assert!( + embedded_provider(&providers, "cohere") + .models + .iter() + .any(|model| model.model_type == "reranker"), + "cohere lost its reranker models" + ); + + for provider in &providers { + for model in &provider.models { + // A :thinking model without a patch must at least alias a real + // wire name (qianwen twins invert a base-model patch instead). + if model.name.ends_with(":thinking") { + assert!( + model.patch.is_some() || model.real_name.is_some(), + "{}:{} has neither patch nor real_name", + provider.provider, + model.name + ); + } + if model.model_type == "chat" { + let serialized = serde_yaml::to_value(model).unwrap(); + assert!( + serialized + .as_mapping() + .unwrap() + .keys() + .any(|key| !matches!(key.as_str(), Some("name" | "type"))), + "{}:{} is an all-default chat entry", + provider.provider, + model.name + ); + } + } + } + + for model in &embedded_provider(&providers, "claude").models { + if model.model_type == "chat" { + assert!( + model.require_max_tokens, + "claude:{} is missing require_max_tokens", + model.name + ); + } + } + } + + #[test] + fn embedded_catalog_roundtrip() { + let providers = embedded_catalog(); + let yaml = serde_yaml::to_string(&providers).unwrap(); + let reparsed: Vec = serde_yaml::from_str(&yaml).unwrap(); + assert_eq!(reparsed.len(), providers.len()); + for (reparsed, original) in reparsed.iter().zip(&providers) { + assert_eq!(reparsed.provider, original.provider); + assert_eq!(reparsed.models.len(), original.models.len()); + } + } + /// Guards against upstream id-shape drift by comparing live API model /// names against the embedded models.yaml. Run manually: /// `cargo test idshape_guard_live -- --ignored --nocapture` diff --git a/src/client/model.rs b/src/client/model.rs index 2c84ec8..cbd9623 100644 --- a/src/client/model.rs +++ b/src/client/model.rs @@ -358,7 +358,7 @@ impl ModelData { #[derive(Debug, Clone, Serialize, Deserialize)] pub struct ProviderModels { pub provider: String, - #[serde(default)] + #[serde(default, skip_serializing_if = "Option::is_none")] pub oauth: Option, pub models: Vec, } diff --git a/src/main.rs b/src/main.rs index 9309149..605c689 100644 --- a/src/main.rs +++ b/src/main.rs @@ -20,7 +20,7 @@ extern crate log; use crate::cli::Cli; use crate::client::{ - ModelType, call_chat_completions, call_chat_completions_streaming, list_models, oauth, + ModelType, call_chat_completions, call_chat_completions_streaming, catalog, list_models, oauth, }; use crate::config::instructions::WORKSPACE_INSTRUCTIONS_FILE_NAME; use crate::config::{ @@ -101,6 +101,7 @@ async fn main() -> Result<()> { let info_flag = cli.info || cli.sync_models + || cli.generate_models.is_some() || cli.list_models || cli.list_roles || cli.list_agents @@ -295,6 +296,10 @@ async fn run( return sync_models(&url, abort_signal.clone()).await; } + if let Some(path) = &cli.generate_models { + return catalog::generate_models_file(path).await; + } + if cli.list_models { for model in list_models(ctx.app.config.as_ref(), ModelType::Chat) { println!("{}", model.id());