Skip to content

chore: update model catalog from bot issues #904

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Erin McNulty (erin2722) merged 2 commits into from
Jul 2, 2026
Merged

chore: update model catalog from bot issues #904

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1f70a30
chore: update model catalog from bot issues
erin2722 Jul 2, 2026
6ca74a2
fix: drop non-invocable mistral-medium-3-5-26-04; align Sonnet 4.6 12…
erin2722 Jul 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions packages/proxy/schema/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -364,7 +364,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"pixtral-large-latest": ["mistral"],
"mistral-medium-latest": ["mistral"],
"mistral-medium-2505": ["mistral"],
"pixtral-large-2411": ["mistral", "vertex"],
"pixtral-large-2411": ["mistral"],
"mistral-small-latest": ["mistral"],
"mistral-small-2501": ["mistral"],
"codestral-2501": ["mistral"],
Expand Down Expand Up @@ -947,7 +947,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"grok-code-fast-1": ["xAI"],
"grok-code-fast": ["xAI"],
"grok-code-fast-1-0825": ["xAI"],
"gemini-3.5-flash": ["google"],
"gemini-3.5-flash": ["google", "vertex"],
"gemini-3.1-flash-image-preview": ["google"],
"gemini-3.1-flash-lite": ["google"],
"gemini-3.1-flash-lite-preview": ["google"],
Expand Down Expand Up @@ -1043,7 +1043,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"databricks-meta-llama-3-3-70b-instruct": ["databricks"],
"databricks-meta-llama-3-1-405b-instruct": ["databricks"],
"databricks-meta-llama-3-1-8b-instruct": ["databricks"],
"openai/gpt-oss-120b": ["together", "groq", "baseten"],
"openai/gpt-oss-120b": ["groq", "together", "baseten"],
"openai/gpt-oss-20b": ["groq"], // NOTE: We use groq pricing for this and Together pricing for the 120B model
"o4-mini-deep-research-2025-06-26": ["openai", "azure"],
"o4-mini-deep-research": ["openai", "azure"],
Expand All @@ -1060,6 +1060,8 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"accounts/fireworks/models/deepseek-v2-lite-chat": ["fireworks"],
"accounts/fireworks/models/kimi-k2-instruct": ["fireworks"],
"grok-latest": ["xAI"],
"gemma-4-31b": ["cerebras"],
"gpt-5.4-mini-2026-03-17": ["openai", "azure"],
};

const modelEndpointAvailableModels = getAvailableModels();
Expand Down
50 changes: 38 additions & 12 deletions packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@
"displayName": "GPT-5.4 mini (2026-03-17)",
"reasoning": true,
"parent": "gpt-5.4-mini",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"available_providers": [
"openai",
Expand Down Expand Up @@ -164,7 +164,7 @@
"input_cache_read_cost_per_mil_tokens": 0.075,
"displayName": "GPT-5.4 mini",
"reasoning": true,
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"available_providers": [
"openai",
Expand All @@ -180,7 +180,7 @@
"input_cache_read_cost_per_mil_tokens": 0.02,
"displayName": "GPT-5.4 nano",
"reasoning": true,
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"available_providers": [
"openai",
Expand Down Expand Up @@ -1313,8 +1313,8 @@
"openai/gpt-oss-120b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.15,
"output_cost_per_mil_tokens": 0.6,
"input_cost_per_mil_tokens": 0.1,
"output_cost_per_mil_tokens": 0.5,
"input_cache_read_cost_per_mil_tokens": 0.1,
"displayName": "OpenAI GPT-OSS (120B)",
"reasoning": true,
Expand Down Expand Up @@ -1655,7 +1655,7 @@
"us.anthropic.claude-sonnet-4-6"
],
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_output_tokens": 128000,

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 2, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Update the Claude 4.6 regional aliases too

When callers use us.anthropic.claude-sonnet-4-6 or global.anthropic.claude-sonnet-4-6 directly, their own model entries still say max_output_tokens: 64000 even though this top-level model now lists them as fallback aliases and is raised to 128k. The Anthropic adapter defaults max_tokens from the selected model spec (openaiParamsToAnthropicMesssageParams), so requests that omit max_tokens for those Bedrock aliases will still be capped at 64k; update the two alias entries along with this value.

Useful? React with 👍 / 👎.

"available_providers": [
"anthropic"
]
Expand Down Expand Up @@ -3249,6 +3249,7 @@
"displayName": "Qwen3-32B",
"reasoning": true,
"experimental": true,
"deprecation_date": "2026-07-17",
"max_input_tokens": 131072,
"max_output_tokens": 40960,
"available_providers": [
Expand Down Expand Up @@ -4084,7 +4085,7 @@
"flavor": "chat",
"input_cost_per_mil_tokens": 0.6,
"output_cost_per_mil_tokens": 3.6,
"input_cache_read_cost_per_mil_tokens": 0.06,
"input_cache_read_cost_per_mil_tokens": 0.35,
"displayName": "Qwen3.5 397B A17B",
"max_input_tokens": 262144,
"available_providers": [
Expand Down Expand Up @@ -4308,6 +4309,7 @@
"flavor": "chat",
"input_cost_per_mil_tokens": 2,
"output_cost_per_mil_tokens": 6,
"deprecation_date": "2026-05-31",
"parent": "mistral-large-latest",
"fallback_models": [
"publishers/mistralai/models/mistral-large-2411"
Expand Down Expand Up @@ -4347,6 +4349,7 @@
"multimodal": true,
"input_cost_per_mil_tokens": 2,
"output_cost_per_mil_tokens": 6,
"deprecation_date": "2026-05-31",
"parent": "pixtral-large-latest",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
Expand All @@ -4361,6 +4364,8 @@
"input_cost_per_mil_tokens": 1.5,
"output_cost_per_mil_tokens": 7.5,
"displayName": "Mistral Medium 3.5",
"reasoning": true,
"reasoning_budget": true,
"max_input_tokens": 256000,
"available_providers": [
"mistral"
Expand All @@ -4386,6 +4391,8 @@
"input_cost_per_mil_tokens": 0.15,
"output_cost_per_mil_tokens": 0.6,
"displayName": "Mistral Small",
"reasoning": true,
"reasoning_budget": true,
"max_input_tokens": 262144,
"max_output_tokens": 131072,
"available_providers": [
Expand Down Expand Up @@ -4666,6 +4673,7 @@
"input_cost_per_mil_tokens": 0.59,
"output_cost_per_mil_tokens": 0.79,
"displayName": "Llama 3.3 70B Versatile 128k",
"deprecation_date": "2026-08-16",
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"available_providers": [
Expand Down Expand Up @@ -4724,6 +4732,7 @@
"output_cost_per_mil_tokens": 0.34,
"displayName": "Llama 4 Scout (17Bx16E)",
"experimental": true,
"deprecation_date": "2026-07-17",
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"available_providers": [
Expand Down Expand Up @@ -4776,6 +4785,8 @@
"input_cost_per_mil_tokens": 1.5,
"output_cost_per_mil_tokens": 7.5,
"displayName": "Mistral Medium 3.5",
"reasoning": true,
"reasoning_budget": true,
"max_input_tokens": 256000,
"available_providers": [
"mistral"
Expand Down Expand Up @@ -6112,6 +6123,7 @@
"input_cache_read_cost_per_mil_tokens": 0.15,
"displayName": "Gemini 3.5 Flash",
"reasoning": true,
"reasoning_budget": true,
"fallback_models": [
"publishers/google/models/gemini-3.5-flash"
],
Expand Down Expand Up @@ -6778,7 +6790,7 @@
"reasoning_budget": true,
"parent": "anthropic.claude-sonnet-4-6",
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_output_tokens": 128000,
"available_providers": [
"bedrock"
]
Expand All @@ -6796,7 +6808,7 @@
"reasoning_budget": true,
"parent": "anthropic.claude-sonnet-4-6",
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_output_tokens": 128000,
"available_providers": [
"bedrock"
]
Expand All @@ -6813,7 +6825,7 @@
"reasoning": true,
"reasoning_budget": true,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_output_tokens": 128000,
"available_providers": [
"bedrock"
]
Expand Down Expand Up @@ -8196,7 +8208,7 @@
"reasoning": true,
"reasoning_budget": true,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_output_tokens": 128000,
"available_providers": [
"vertex"
]
Expand Down Expand Up @@ -9393,7 +9405,7 @@
"flavor": "chat",
"input_cost_per_mil_tokens": 1.4,
"output_cost_per_mil_tokens": 4.4,
"input_cache_read_cost_per_mil_tokens": 0.26,
"input_cache_read_cost_per_mil_tokens": 0.14,
"displayName": "GLM 5.2",
"reasoning": true,
"max_input_tokens": 1048576,
Expand Down Expand Up @@ -12297,5 +12309,19 @@
"available_providers": [
"vertex"
]
},
"gemma-4-31b": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.99,
"output_cost_per_mil_tokens": 1.49,
"displayName": "Gemma 4 31B",
"reasoning": true,
"max_input_tokens": 131072,
"max_output_tokens": 40960,
"available_providers": [
"cerebras"
]
}
}
Loading