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.
This commit is contained in:
8 files changed
+10276
-3058
No files matched your search
+592
@@ -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:
|
||||
|
||||
Reference in new issue
Block a user