Skip to content

chore: sync new models #1225

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
Sep 9, 2026
Merged

chore: sync new models #1225

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
2 changes: 2 additions & 0 deletions packages/proxy/schema/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -394,6 +394,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"mixtral-8x7b": ["lepton"],
"wizardlm-2-7b": ["lepton"],
"wizardlm-2-8x22b": ["lepton", "openrouter"],
"inception/mercury-2.5": ["openrouter"],

@chatgpt-codex-connector chatgpt-codex-connector Bot Sep 9, 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 provider-routing changes in gateway

For this catalog-sync change, adding inception/mercury-2.5 here—and likewise north-small-translate-09-2026 below—modifies provider routing in the deprecated proxy. Repository guidance reserves routing work for ../gateway/ and permits only model_list.json updates here without an explicit deprecated-proxy request, so remove both AvailableEndpointTypes additions and apply any required routing update in the parent gateway instead.

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

Useful? React with 👍 / 👎.

"openai/gpt-6-astra-pro": ["openrouter"],
"qwen/qwen3.8-max-0902": ["openrouter"],
"inclusionai/ling-3.0-flash-fin": ["openrouter"],
Expand Down Expand Up @@ -1345,6 +1346,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"command-r-plus-08-2024": ["cohere", "openrouter"],
"command-r-08-2024": ["cohere", "openrouter"],
"command-r7b-12-2024": ["cohere", "openrouter"],
"north-small-translate-09-2026": ["cohere"],
"c4ai-aya-expanse-32b": ["cohere"],
"c4ai-aya-vision-32b": ["cohere"],
"command-a-plus-05-2026": ["cohere"],
Expand Down
43 changes: 33 additions & 10 deletions packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10554,6 +10554,15 @@
"bedrock"
]
},
"north-small-translate-09-2026": {
"format": "openai",
"flavor": "chat",
"displayName": "North Small Translate (09-2026)",
"max_input_tokens": 32768,
"available_providers": [
"cohere"
]
},
"tiny-aya-water": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -13906,6 +13915,20 @@
"openrouter"
]
},
"inception/mercury-2.5": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.04,
"output_cost_per_mil_tokens": 0.15,
"input_cache_read_cost_per_mil_tokens": 0.004,
"displayName": "Inception: Mercury 2.5",
"reasoning": true,
"max_input_tokens": 260000,
"max_output_tokens": 65536,
"available_providers": [
"openrouter"
]
},
"inception/mercury-2.5-preview": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -14942,9 +14965,9 @@
"ibm-granite/granite-4.2-8b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.1,
"output_cost_per_mil_tokens": 0.15,
"input_cache_read_cost_per_mil_tokens": 0.05,
"input_cost_per_mil_tokens": 0.06,
"output_cost_per_mil_tokens": 0.25,
"input_cache_read_cost_per_mil_tokens": 0.015,
"displayName": "IBM: Granite 4.2 8B",
"reasoning": true,
"max_input_tokens": 131072,
Expand Down Expand Up @@ -15065,7 +15088,7 @@
"minimax/minimax-m1": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.4,
"input_cost_per_mil_tokens": 0.55,
"output_cost_per_mil_tokens": 2.2,
"displayName": "MiniMax: MiniMax M1",
"reasoning": true,
Expand Down Expand Up @@ -15233,9 +15256,9 @@
"z-ai/glm-4.6": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.55,
"output_cost_per_mil_tokens": 2.2,
"input_cache_read_cost_per_mil_tokens": 0.11,
"input_cost_per_mil_tokens": 0.43,
"output_cost_per_mil_tokens": 1.75,
"input_cache_read_cost_per_mil_tokens": 0.08,
"displayName": "Z.ai: GLM 4.6",
"reasoning": true,
"max_input_tokens": 204800,
Expand Down Expand Up @@ -16408,8 +16431,8 @@
"qwen/qwen3-235b-a22b-2507": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.09,
"output_cost_per_mil_tokens": 0.55,
"input_cost_per_mil_tokens": 0.22,
"output_cost_per_mil_tokens": 0.88,
"input_cache_read_cost_per_mil_tokens": 0.0175,
"displayName": "Qwen: Qwen3 235B A22B Instruct (2507)",
"parent": "qwen/qwen3-235b-a22b",
Expand Down Expand Up @@ -16497,7 +16520,7 @@
"qwen/qwen3-next-80b-a3b-instruct": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.1,
"input_cost_per_mil_tokens": 0.09,
"output_cost_per_mil_tokens": 1.1,
"input_cache_read_cost_per_mil_tokens": 0.07,
"displayName": "Qwen: Qwen3 Next 80B A3B Instruct",
Expand Down