Skip to content

chore: update model catalog from bot issues #1173

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 1 commit into from
Aug 27, 2026
Merged

chore: update model catalog from bot issues #1173

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion packages/proxy/schema/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -914,7 +914,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"zai-org/GLM-5.1": ["together"],
"zai-org/GLM-5.2": ["baseten", "together"],
"zai-org/GLM-5.2-Fast": ["baseten"],
"zai-org/GLM-5.3-Flash": ["baseten"],
"zai-org/GLM-5.3-Flash": ["baseten", "together"],

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 27, 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.

P1 Badge Move endpoint mappings to gateway

This change updates AvailableEndpointTypes in the deprecated proxy; the same issue also applies to the new Databricks mapping later in this object. Provider-routing changes belong in the parent ../gateway/ implementation, while only the model_list.json catalog updates should remain in this repository.

AGENTS.md reference: AGENTS.md:L6-L15

Useful? React with 👍 / 👎.

"MiniMaxAI/MiniMax-M2.7": ["together"],
"MiniMaxAI/MiniMax-M3": ["together"],
"mistral-medium-2508": ["mistral"],
Expand Down Expand Up @@ -1384,6 +1384,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"gemini-2.5-flash-lite": ["google", "openrouter"],
"gemini-2.5-pro": ["google", "openrouter"],
"databricks-deepseek-v4-pro-0813": ["databricks"],
"databricks-grok-4-6": ["databricks"],
};

const modelEndpointAvailableModels = getAvailableModels();
Expand Down
52 changes: 35 additions & 17 deletions packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10912,7 +10912,8 @@
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"available_providers": [
"baseten"
"baseten",
"together"
]
},
"zai-org/GLM-5.2": {
Expand Down Expand Up @@ -11082,6 +11083,7 @@
"multimodal": true,
"input_cost_per_mil_tokens": 0.5,
"output_cost_per_mil_tokens": 1.5,
"input_cache_read_cost_per_mil_tokens": 0.05,
"displayName": "Mistral Large",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
Expand Down Expand Up @@ -11109,6 +11111,7 @@
"multimodal": true,
"input_cost_per_mil_tokens": 1.5,
"output_cost_per_mil_tokens": 7.5,
"input_cache_read_cost_per_mil_tokens": 0.15,
"displayName": "Mistral Medium 3.5",
"reasoning": true,
"reasoning_budget": true,
Expand Down Expand Up @@ -11207,6 +11210,8 @@
"input_cost_per_mil_tokens": 2,
"output_cost_per_mil_tokens": 5,
"displayName": "Magistral Medium Latest",
"deprecated": true,
"deprecation_date": "2026-07-31",
"max_input_tokens": 128000,
"max_output_tokens": 40000,
"available_providers": [
Expand Down Expand Up @@ -11317,6 +11322,7 @@
"multimodal": true,
"input_cost_per_mil_tokens": 0.15,
"output_cost_per_mil_tokens": 0.6,
"input_cache_read_cost_per_mil_tokens": 0.015,
"displayName": "Mistral Small",
"reasoning": true,
"reasoning_budget": true,
Expand Down Expand Up @@ -11348,6 +11354,8 @@
"input_cost_per_mil_tokens": 0.5,
"output_cost_per_mil_tokens": 1.5,
"displayName": "Magistral Small Latest",
"deprecated": true,
"deprecation_date": "2026-07-31",
"max_input_tokens": 128000,
"max_output_tokens": 40000,
"available_providers": [
Expand Down Expand Up @@ -12612,6 +12620,16 @@
"openrouter"
]
},
"databricks-grok-4-6": {
"format": "openai",
"flavor": "chat",
"displayName": "Grok 4.6",
"reasoning": true,
"max_input_tokens": 500000,
"available_providers": [
"databricks"
]
},
"databricks-deepseek-v4-pro-0813": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -13325,6 +13343,22 @@
"databricks"
]
},
"qwen/qwen3.8-27b": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.8,
"output_cost_per_mil_tokens": 4,
"input_cache_read_cost_per_mil_tokens": 0.4,
"displayName": "Qwen: Qwen3.8 27B",
"reasoning": true,
"max_input_tokens": 131042,
"max_output_tokens": 16384,
"available_providers": [
"groq",
"openrouter"
]
},
"stealth/ox-alpha": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -15678,22 +15712,6 @@
"openrouter"
]
},
"qwen/qwen3.8-27b": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.8,
"output_cost_per_mil_tokens": 4,
"input_cache_read_cost_per_mil_tokens": 0.4,
"displayName": "Qwen: Qwen3.8 27B",
"reasoning": true,
"max_input_tokens": 131042,
"max_output_tokens": 16384,
"available_providers": [
"groq",
"openrouter"
]
},
"qwen/qwen3.8-2.4t-a95b": {
"format": "openai",
"flavor": "chat",
Expand Down