From f1146bb2b9dc48b9c7a19d2496724abec1ebe1fc Mon Sep 17 00:00:00 2001 From: Alex Clarke Date: Thu, 16 Oct 2025 15:20:33 -0600 Subject: [PATCH] chore: update the models.yaml --- models.yaml | 330 +++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 252 insertions(+), 78 deletions(-) diff --git a/models.yaml b/models.yaml index de85fdf..22280a7 100644 --- a/models.yaml +++ b/models.yaml @@ -31,6 +31,13 @@ output_price: 0.4 supports_vision: true supports_function_calling: true + - name: gpt-5-codex + max_input_tokens: 400000 + max_output_tokens: 128000 + input_price: 1.25 + output_price: 10 + supports_vision: true + supports_function_calling: true - name: gpt-4.1 max_input_tokens: 1047576 max_output_tokens: 32768 @@ -228,6 +235,30 @@ # - https://docs.anthropic.com/en/api/messages - provider: claude models: + - 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-opus-4-1-20250805 max_input_tokens: 200000 max_output_tokens: 8192 @@ -463,26 +494,31 @@ input_price: 3 output_price: 15 supports_function_calling: true + - name: grok-4-fast-non-reasoning + max_input_tokens: 2000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true + - name: grok-4-fast-reasoning + max_input_tokens: 2000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true + - name: grok-code-fast + 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-fast - max_input_tokens: 131072 - input_price: 5 - output_price: 25 - supports_function_calling: true - name: grok-3-mini max_input_tokens: 131072 input_price: 0.3 output_price: 0.5 supports_function_calling: true - - name: grok-3-mini-fast - max_input_tokens: 131072 - input_price: 0.6 - output_price: 4 - supports_function_calling: true # Links: # - https://docs.perplexity.ai/getting-started/models @@ -542,8 +578,8 @@ input_price: 0 output_price: 0 supports_function_calling: true - - name: moonshotai/kimi-k2-instruct - max_input_tokens: 131072 + - name: moonshotai/kimi-k2-instruct-0905 + max_input_tokens: 262144 input_price: 0 output_price: 0 supports_function_calling: true @@ -551,11 +587,11 @@ max_input_tokens: 131072 input_price: 0 output_price: 0 - - name: compound-beta + - name: groq/compound max_input_tokens: 131072 input_price: 0 output_price: 0 - - name: compound-beta-mini + - name: groq/compound-mini max_input_tokens: 131072 input_price: 0 output_price: 0 @@ -601,6 +637,29 @@ output_price: 0.3 supports_vision: true supports_function_calling: true + - 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-opus-4-1@20250805 max_input_tokens: 200000 max_output_tokens: 8192 @@ -733,6 +792,31 @@ # - https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-call.html - provider: bedrock models: + - 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-opus-4-1-20250805-v1:0 max_input_tokens: 200000 max_output_tokens: 8192 @@ -980,7 +1064,6 @@ 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 @@ -1034,6 +1117,31 @@ input_price: 0.21 output_price: 0.63 supports_vision: true + - name: qwen3-max + max_input_tokens: 262144 + input_price: 2.1 + output_price: 8.4 + supports_function_calling: true + - name: qwen3-vl-plus + max_input_tokens: 262144 + input_price: 0.42 + output_price: 4.2 + supports_vision: true + - name: qwen3-max-preview + max_input_tokens: 262144 + max_output_tokens: 32768 + input_price: 1.4 + output_price: 5.6 + 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 @@ -1051,22 +1159,15 @@ - name: qwen3-30b-a3b-thinking-2507 max_input_tokens: 131072 input_price: 0.105 - output_price: 1.05 - - name: qwen3-235b-a22b - max_input_tokens: 131072 - max_output_tokens: 8192 - input_price: 0.56 - output_price: 1.68 - - name: qwen3-30b-a3b - max_input_tokens: 131072 - max_output_tokens: 8192 - input_price: 0.21 - output_price: 0.84 - - name: qwen3-32b - max_input_tokens: 131072 - max_output_tokens: 8192 - input_price: 0.28 - output_price: 1.12 + output_price: 1.05 + - name: qwen3-coder-480b-a35b-instruct + max_input_tokens: 262144 + input_price: 1.26 + output_price: 5.04 + - name: qwen3-coder-30b-a3b-instruct + max_input_tokens: 262144 + input_price: 0.315 + output_price: 1.26 - name: qwen2.5-72b-instruct max_input_tokens: 129024 max_output_tokens: 8192 @@ -1085,10 +1186,10 @@ input_price: 0.49 output_price: 0.98 supports_function_calling: true - - name: deepseek-v3 - max_input_tokens: 65536 - input_price: 0.14 - output_price: 0.56 + - name: deepseek-v3.1 + max_input_tokens: 131072 + input_price: 0.28 + output_price: 1.12 - name: deepseek-r1-0528 max_input_tokens: 65536 input_price: 0.28 @@ -1152,8 +1253,8 @@ output_price: 4.2 supports_vision: true supports_function_calling: true - - name: kimi-k2-0711-preview - max_input_tokens: 131072 + - name: kimi-k2-0905-preview + max_input_tokens: 262144 input_price: 0.56 output_price: 2.24 supports_vision: true @@ -1192,6 +1293,11 @@ # - https://open.bigmodel.cn/dev/api#glm-4 - provider: zhipuai models: + - name: glm-4.5 + max_input_tokens: 202752 + input_price: 0.28 + output_price: 1.12 + supports_function_calling: true - name: glm-4.5 max_input_tokens: 131072 input_price: 0.28 @@ -1247,7 +1353,7 @@ input_price: 0.112 # Links: -# - https://platform.minimaxi.com/document/Price +# - https://platform.minimaxi.com/document/pricing # - https://platform.minimaxi.com/document/ChatCompletion%20v2 - provider: minimax models: @@ -1294,6 +1400,13 @@ output_price: 0.4 supports_vision: true supports_function_calling: true + - name: openai/gpt-5-codex + max_input_tokens: 400000 + max_output_tokens: 128000 + input_price: 1.25 + output_price: 10 + supports_vision: true + supports_function_calling: true - name: openai/gpt-4.1 max_input_tokens: 1047576 max_output_tokens: 32768 @@ -1442,6 +1555,14 @@ max_input_tokens: 131072 input_price: 0.1 output_price: 0.2 + - 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-opus-4.1 max_input_tokens: 200000 max_output_tokens: 8192 @@ -1556,15 +1677,18 @@ max_output_tokens: 4096 input_price: 0.0375 output_price: 0.15 + - name: deepseek/deepseek-v3.2-exp + max_input_tokens: 163840 + input_price: 0.27 + output_price: 0.40 + - name: deepseek/deepseek-v3.1-terminus + max_input_tokens: 163840 + input_price: 0.23 + output_price: 0.90 - name: deepseek/deepseek-chat-v3.1 max_input_tokens: 163840 input_price: 0.2 output_price: 0.8 - - name: deepseek/deepseek-chat-v3-0324 - max_input_tokens: 64000 - input_price: 0.27 - output_price: 1.1 - supports_function_calling: true - name: deepseek/deepseek-r1-0528 max_input_tokens: 128000 input_price: 0.50 @@ -1595,6 +1719,20 @@ input_price: 0.21 output_price: 0.63 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-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 max_input_tokens: 262144 input_price: 0.12 @@ -1608,23 +1746,25 @@ max_input_tokens: 131072 input_price: 0.2 output_price: 0.8 - - name: qwen/qwen3-coder + - name: qwen/qwen3-30b-a3b-thinking-2507 max_input_tokens: 262144 - input_price: 0.3 - output_price: 1.2 + input_price: 0.071 + output_price: 0.285 + - 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-30b-a3b-instruct + max_input_tokens: 262144 + input_price: 0.052 + output_price: 0.207 supports_function_calling: true - - name: qwen/qwen3-235b-a22b - max_input_tokens: 40960 - input_price: 0.15 - output_price: 0.6 - - name: qwen/qwen3-30b-a3b - max_input_tokens: 40960 - input_price: 0.1 - output_price: 0.3 - - name: qwen/qwen3-32b - max_input_tokens: 40960 - input_price: 0.1 - output_price: 0.3 - name: qwen/qwen-2.5-72b-instruct max_input_tokens: 131072 input_price: 0.35 @@ -1639,25 +1779,31 @@ max_input_tokens: 32768 input_price: 0.18 output_price: 0.18 - - name: moonshotai/kimi-k2 - max_input_tokens: 63000 - input_price: 0.14 - output_price: 2.49 + - name: moonshotai/kimi-k2-0905 + max_input_tokens: 262144 + input_price: 0.296 + output_price: 1.185 + supports_function_calling: true + - name: moonshotai/kimi-dev-72b + max_input_tokens: 131072 + input_price: 0.29 + output_price: 1.15 supports_function_calling: true - name: x-ai/grok-4 max_input_tokens: 256000 input_price: 3 output_price: 15 supports_function_calling: true - - name: x-ai/grok-3 - max_input_tokens: 131072 - input_price: 3 - output_price: 15 - supports_function_calling: true - - name: x-ai/grok-3-mini - max_input_tokens: 131072 - input_price: 0.3 + - name: x-ai/grok-4-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-pro-v1 max_input_tokens: 300000 max_output_tokens: 5120 @@ -1708,6 +1854,11 @@ max_input_tokens: 1000192 input_price: 0.2 output_price: 1.1 + - name: z-ai/glm-4.6 + max_input_tokens: 202752 + input_price: 0.5 + output_price: 1.75 + supports_function_calling: true - name: z-ai/glm-4.5 max_input_tokens: 131072 input_price: 0.2 @@ -1921,6 +2072,15 @@ max_input_tokens: 131072 input_price: 0.23 output_price: 0.40 + - 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 @@ -1935,6 +2095,11 @@ 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/Qwen3-235B-A22B max_input_tokens: 40960 input_price: 0.15 @@ -1956,14 +2121,18 @@ max_input_tokens: 32768 input_price: 0.07 output_price: 0.16 + - name: deepseek-ai/DeepSeek-V3.2-Exp + max_input_tokens: 163840 + input_price: 0.27 + output_price: 0.40 + - name: deepseek-ai/DeepSeek-V3.1-Terminus + max_input_tokens: 163840 + input_price: 0.27 + output_price: 1.0 - name: deepseek-ai/DeepSeek-V3.1 max_input_tokens: 163840 input_price: 0.3 output_price: 1.0 - - name: deepseek-ai/DeepSeek-V3-0324 - max_input_tokens: 163840 - input_price: 0.40 - output_price: 0.89 - name: deepseek-ai/DeepSeek-R1-0528 max_input_tokens: 163840 input_price: 0.5 @@ -1980,10 +2149,15 @@ max_input_tokens: 131072 input_price: 0.07 output_price: 0.28 - - name: moonshotai/Kimi-K2-Instruct - max_input_tokens: 131072 - input_price: 0.55 - output_price: 2.2 + - name: moonshotai/Kimi-K2-Instruct-0905 + max_input_tokens: 262144 + input_price: 0.5 + output_price: 2.0 + supports_function_calling: true + - name: zai-org/GLM-4.6 + max_input_tokens: 202752 + input_price: 0.6 + output_price: 1.9 supports_function_calling: true - name: zai-org/GLM-4.5 max_input_tokens: 131072