Skip to content

chore: sync new models #1168

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 5 commits into from
Aug 26, 2026
Merged

chore: sync new models #1168

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
d56943d
chore: sync new models
erin2722 Aug 26, 2026
b6fbd0e
catalog: drop stale cache-read on qwen2.5-vl-72b-instruct
erin2722 Aug 26, 2026
408fbe9
chore: sync new models
erin2722 Aug 26, 2026
b77ba00
catalog: add groq to qwen3.8-27b + add baseten GLM-5.3-Flash
erin2722 Aug 26, 2026
270b86c
Merge branch 'chore/sync-new-models' of https://github.com/braintrust…
erin2722 Aug 26, 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
5 changes: 4 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 @@ -393,6 +393,8 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"mixtral-8x7b": ["lepton"],
"wizardlm-2-7b": ["lepton"],
"wizardlm-2-8x22b": ["lepton", "openrouter"],
"qwen/qwen3.8-flash": ["openrouter"],
"z-ai/glm-5.3-flash": ["openrouter"],
Comment on lines +396 to +397

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 26, 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 Keep model sync out of legacy endpoint routing

These entries modify AvailableEndpointTypes in the deprecated proxy even though both new records already declare openrouter through available_providers in model_list.json. Repository policy allows catalog changes here but requires routing changes to be made in the parent gateway, so remove these legacy mappings and apply any necessary routing update in ../gateway/ instead.

AGENTS.md reference: AGENTS.md:L10-L15

Useful? React with 👍 / 👎.

"meta/muse-spark-1.2-contributor": ["openrouter"],
"deepseek/deepseek-v4-flash-vision-exp": ["openrouter"],
"tencent/hy-mt2-7b": ["openrouter"],
Expand All @@ -401,7 +403,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"tencent/hy-mt2-30b-a3b": ["openrouter"],
"mistralai/ministral-8b": ["openrouter"],
"z-ai/glm-5.3": ["openrouter"],
"qwen/qwen3.8-27b": ["openrouter"],
"qwen/qwen3.8-27b": ["groq", "openrouter"],
"bytedance-seed/seed-2-1-turbo": ["openrouter"],
"qwen/qwen3.8-2.4t-a95b": ["openrouter"],
"bytedance-seed/seed-2.0-code": ["openrouter"],
Expand Down Expand Up @@ -912,6 +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"],
"MiniMaxAI/MiniMax-M2.7": ["together"],
"MiniMaxAI/MiniMax-M3": ["together"],
"mistral-medium-2508": ["mistral"],
Expand Down
68 changes: 57 additions & 11 deletions packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10900,6 +10900,21 @@
"baseten"
]
},
"zai-org/GLM-5.3-Flash": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.15,
"output_cost_per_mil_tokens": 0.5,
"input_cache_read_cost_per_mil_tokens": 0.03,
"displayName": "GLM 5.3 Flash",
"reasoning": true,
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"available_providers": [
"baseten"
]
},
"zai-org/GLM-5.2": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -14231,9 +14246,9 @@
"deepseek/deepseek-v4-flash": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.0826,
"output_cost_per_mil_tokens": 0.1652,
"input_cache_read_cost_per_mil_tokens": 0.01652,
"input_cost_per_mil_tokens": 0.07952,
"output_cost_per_mil_tokens": 0.15904,
"input_cache_read_cost_per_mil_tokens": 0.015904,
"displayName": "DeepSeek: DeepSeek V4 Flash",
"reasoning": true,
"max_input_tokens": 1048576,
Expand Down Expand Up @@ -14593,6 +14608,21 @@
"openrouter"
]
},
"z-ai/glm-5.3-flash": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.075,
"output_cost_per_mil_tokens": 0.25,
"input_cache_read_cost_per_mil_tokens": 0.015,
"displayName": "Z.ai: GLM 5.3 Flash",
"reasoning": true,
"max_input_tokens": 1310720,
"max_output_tokens": 131072,
"available_providers": [
"openrouter"
]
},
"z-ai/glm-5.3": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -14904,9 +14934,9 @@
"tencent/hy3": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.132,
"output_cost_per_mil_tokens": 0.528,
"input_cache_read_cost_per_mil_tokens": 0.033,
"input_cost_per_mil_tokens": 0.0825,
"output_cost_per_mil_tokens": 0.33,
"input_cache_read_cost_per_mil_tokens": 0.020625,
"displayName": "Tencent: Hy3",
"reasoning": true,
"max_input_tokens": 262144,
Expand Down Expand Up @@ -15633,18 +15663,34 @@
"openrouter"
]
},
"qwen/qwen3.8-flash": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.16,
"output_cost_per_mil_tokens": 0.47,
"input_cache_read_cost_per_mil_tokens": 0.016,
"displayName": "Qwen: Qwen3.8 Flash",
"reasoning": true,
"max_input_tokens": 1000000,
"max_output_tokens": 131072,
"available_providers": [
"openrouter"
]
},
"qwen/qwen3.8-27b": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.425,
"output_cost_per_mil_tokens": 2.55,
"input_cache_read_cost_per_mil_tokens": 0.085,
"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": 262144,
"max_output_tokens": 131072,
"max_input_tokens": 131042,
"max_output_tokens": 16384,
"available_providers": [
"groq",
"openrouter"
]
},
Expand Down
Loading