Skip to content

chore: sync new models #1239

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
Sep 15, 2026
Merged

chore: sync new models #1239

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
4609003
chore: sync new models
erin2722 Sep 15, 2026
cbbb3ef
chore: exclude non-invokable OpenAI models
erin2722 Sep 15, 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
3 changes: 3 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 @@ -395,6 +395,9 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"mixtral-8x7b": ["lepton"],
"wizardlm-2-7b": ["lepton"],
"wizardlm-2-8x22b": ["lepton", "openrouter"],
"inference-net/schematron-v2-turbo": ["openrouter"],
"inference-net/schematron-v2-small": ["openrouter"],
"inclusionai/ling-3.0-flash-vl": ["openrouter"],
Comment on lines +398 to +400

@chatgpt-codex-connector chatgpt-codex-connector Bot Sep 12, 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 new endpoint routing out of the deprecated proxy

These entries add OpenRouter provider routing for the three new model IDs inside the deprecated proxy. Repository guidance explicitly directs model-routing changes to the parent gateway/ directory and makes an exception here only for model_list.json; keep the catalog additions, but move or implement the routing changes in the active gateway instead.

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

Useful? React with 👍 / 👎.

"sakana/fugu-ultra-v2": ["openrouter"],
"sakana/fugu-max": ["openrouter"],
"deepseek/deepseek-v4.1-flash": ["openrouter"],
Expand Down
128 changes: 87 additions & 41 deletions packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1119,7 +1119,7 @@
"gpt-4o-mini-tts": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 2.5,
"input_cost_per_mil_tokens": 0.6,
"output_cost_per_mil_tokens": 10,
"displayName": "GPT-4o mini TTS",
"available_providers": [
Expand Down Expand Up @@ -1188,7 +1188,7 @@
"gpt-4o-mini-tts-2025-12-15": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 2.5,
"input_cost_per_mil_tokens": 0.6,
"output_cost_per_mil_tokens": 10,
"displayName": "GPT-4o mini TTS (2025-12-15)",
"parent": "gpt-4o-mini-tts",
Expand Down Expand Up @@ -1230,7 +1230,7 @@
"gpt-4o-mini-tts-2025-03-20": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 2.5,
"input_cost_per_mil_tokens": 0.6,
"output_cost_per_mil_tokens": 10,
"displayName": "GPT-4o mini TTS (2025-03-20)",
"deprecation_date": "2026-07-23",
Expand Down Expand Up @@ -2440,6 +2440,7 @@
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 5,
"output_cost_per_mil_tokens": 10,
"input_cache_read_cost_per_mil_tokens": 1.25,
"displayName": "ChatGPT Image",
"deprecation_date": "2026-12-01",
Expand Down Expand Up @@ -2957,6 +2958,7 @@
"displayName": "DeepSeek V4.1 Flash",
"reasoning": true,
"max_input_tokens": 1048576,
"max_output_tokens": 393216,
"available_providers": [
"fireworks"
]
Expand Down Expand Up @@ -3117,9 +3119,9 @@
"accounts/fireworks/models/deepseek-v4-pro": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 1.74,
"output_cost_per_mil_tokens": 3.48,
"input_cache_read_cost_per_mil_tokens": 0.145,
"input_cost_per_mil_tokens": 1.2,
"output_cost_per_mil_tokens": 1.2,
"input_cache_read_cost_per_mil_tokens": 0.6,
"displayName": "DeepSeek V4 Pro",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
Expand Down Expand Up @@ -3662,6 +3664,8 @@
"accounts/fireworks/models/qwen3-reranker-8b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.2,
"displayName": "Qwen3 Reranker 8B",
"max_input_tokens": 40960,
"max_output_tokens": 40960,
"available_providers": [
Expand Down Expand Up @@ -12524,6 +12528,7 @@
"format": "openai",
"flavor": "chat",
"displayName": "Grok Imagine Image Quality",
"deprecation_date": "2026-11-02",
"available_providers": [
"xAI"
]
Expand Down Expand Up @@ -14028,6 +14033,32 @@
"openrouter"
]
},
"inference-net/schematron-v2-small": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.05,
"output_cost_per_mil_tokens": 0.23,
"input_cache_read_cost_per_mil_tokens": 0.05,
"displayName": "Inference.net: Schematron V2 Small",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"available_providers": [
"openrouter"
]
},
"inference-net/schematron-v2-turbo": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.03,
"output_cost_per_mil_tokens": 0.15,
"input_cache_read_cost_per_mil_tokens": 0.03,
"displayName": "Inference.net: Schematron V2 Turbo",
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"available_providers": [
"openrouter"
]
},
"inception/mercury-2.5": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -14232,8 +14263,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.2,
"output_cost_per_mil_tokens": 0.696,
"input_cost_per_mil_tokens": 0.1875,
"output_cost_per_mil_tokens": 0.6525,
"displayName": "Meta: Llama 4 Maverick",
"max_input_tokens": 1048576,
"max_output_tokens": 16384,
Expand Down Expand Up @@ -14676,8 +14707,8 @@
"nvidia/nemotron-3-super-120b-a12b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.085,
"output_cost_per_mil_tokens": 0.4,
"input_cost_per_mil_tokens": 0.08,
"output_cost_per_mil_tokens": 0.45,
"displayName": "NVIDIA: Nemotron 3 Super 120B A12B",
"reasoning": true,
"max_input_tokens": 1000000,
Expand Down Expand Up @@ -14790,9 +14821,9 @@
"deepseek/deepseek-v4-pro-0813": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.66,
"output_cost_per_mil_tokens": 1.98,
"input_cache_read_cost_per_mil_tokens": 0.066,
"input_cost_per_mil_tokens": 0.9834,
"output_cost_per_mil_tokens": 2.9502,
"input_cache_read_cost_per_mil_tokens": 0.03278,
"displayName": "DeepSeek: DeepSeek V4 Pro (0813)",
"reasoning": true,
"parent": "deepseek/deepseek-v4-pro",
Expand All @@ -14805,9 +14836,9 @@
"deepseek/deepseek-v4-flash-0731": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.065,
"output_cost_per_mil_tokens": 0.18,
"input_cache_read_cost_per_mil_tokens": 0.016,
"input_cost_per_mil_tokens": 0.06,
"output_cost_per_mil_tokens": 0.12,
"input_cache_read_cost_per_mil_tokens": 0.012,
"displayName": "DeepSeek: DeepSeek V4 Flash (0731)",
"reasoning": true,
"parent": "deepseek/deepseek-v4-flash",
Expand Down Expand Up @@ -14943,9 +14974,9 @@
"deepseek/deepseek-v4-pro": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.95526,
"output_cost_per_mil_tokens": 1.91052,
"input_cache_read_cost_per_mil_tokens": 0.079605,
"input_cost_per_mil_tokens": 1.6,
"output_cost_per_mil_tokens": 3.2,
"input_cache_read_cost_per_mil_tokens": 0.135,
"displayName": "DeepSeek: DeepSeek V4 Pro",
"reasoning": true,
"max_input_tokens": 1048576,
Expand Down Expand Up @@ -15129,6 +15160,21 @@
"openrouter"
]
},
"inclusionai/ling-3.0-flash-vl": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.06,
"output_cost_per_mil_tokens": 0.18,
"input_cache_read_cost_per_mil_tokens": 0.012,
"displayName": "inclusionAI: Ling 3.0 Flash VL",
"reasoning": true,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"available_providers": [
"openrouter"
]
},
"inclusionai/ling-3.0-flash-fin": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -15269,9 +15315,9 @@
"minimax/minimax-m2.5": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.3,
"output_cost_per_mil_tokens": 1.2,
"input_cache_read_cost_per_mil_tokens": 0.03,
"input_cost_per_mil_tokens": 0.27,
"output_cost_per_mil_tokens": 1.08,
"input_cache_read_cost_per_mil_tokens": 0.027,
"displayName": "MiniMax: MiniMax M2.5",
"reasoning": true,
"max_input_tokens": 204800,
Expand Down Expand Up @@ -15498,9 +15544,9 @@
"z-ai/glm-5.2": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.966,
"output_cost_per_mil_tokens": 3.036,
"input_cache_read_cost_per_mil_tokens": 0.1932,
"input_cost_per_mil_tokens": 1.4,
"output_cost_per_mil_tokens": 4.4,
"input_cache_read_cost_per_mil_tokens": 0.14,
"displayName": "Z.ai: GLM-5.2",
"reasoning": true,
"max_input_tokens": 1048576,
Expand Down Expand Up @@ -15986,8 +16032,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.3,
"output_cost_per_mil_tokens": 1.1,
"input_cost_per_mil_tokens": 0.35,
"output_cost_per_mil_tokens": 1.5,
"input_cache_read_cost_per_mil_tokens": 0.04,
"displayName": "Meta: Muse Glimmer 30B",
"reasoning": true,
Expand Down Expand Up @@ -16111,9 +16157,9 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 2.34,
"output_cost_per_mil_tokens": 11.7,
"input_cache_read_cost_per_mil_tokens": 0.261,
"input_cost_per_mil_tokens": 2.64813806,
"output_cost_per_mil_tokens": 13.28272425,
"input_cache_read_cost_per_mil_tokens": 0.30264435,
"displayName": "MoonshotAI: Kimi K3",
"reasoning": true,
"max_input_tokens": 1048576,
Expand Down Expand Up @@ -16551,8 +16597,8 @@
"qwen/qwen3-14b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.2275,
"output_cost_per_mil_tokens": 0.91,
"input_cost_per_mil_tokens": 0.12,
"output_cost_per_mil_tokens": 0.24,
"displayName": "Qwen: Qwen3 14B",
"reasoning": true,
"max_input_tokens": 131072,
Expand Down Expand Up @@ -16590,8 +16636,8 @@
"qwen/qwen3-235b-a22b-2507": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.22,
"output_cost_per_mil_tokens": 0.88,
"input_cost_per_mil_tokens": 0.0875,
"output_cost_per_mil_tokens": 0.35,
"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 @@ -16630,9 +16676,9 @@
"qwen/qwen3-30b-a3b-instruct-2507": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.09,
"output_cost_per_mil_tokens": 0.3,
"displayName": "Qwen: Qwen3 30B A3B Instruct 2507",
"input_cost_per_mil_tokens": 0.04815,
"output_cost_per_mil_tokens": 0.19305,
"displayName": "Qwen: Qwen3 30B A3B Instruct (2507)",
"max_input_tokens": 262144,
"max_output_tokens": 32000,
"available_providers": [
Expand Down Expand Up @@ -16937,8 +16983,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.3125,
"output_cost_per_mil_tokens": 1.25,
"input_cost_per_mil_tokens": 0.1625,
"output_cost_per_mil_tokens": 1.3,
"input_cache_read_cost_per_mil_tokens": 0.15625,
"displayName": "Qwen: Qwen3.5 35B A3B",
"reasoning": true,
Expand Down Expand Up @@ -17172,8 +17218,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.042,
"output_cost_per_mil_tokens": 0.22,
"input_cost_per_mil_tokens": 0.09,
"output_cost_per_mil_tokens": 0.3,
"input_cache_read_cost_per_mil_tokens": 0.05,
"displayName": "Google: Gemma 4 26B A4B IT",
"reasoning": true,
Expand Down
5 changes: 5 additions & 0 deletions packages/proxy/scripts/sync_models.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,6 +200,11 @@ const MANUAL_SYNC_EXCLUDED_MODELS: ReadonlyArray<string> = [
"gpt-realtime-translate",
"gpt-transcribe",
"gpt-live-transcribe",
// OpenAI models that are not invocable through supported proxy endpoints.
"computer-use-preview",
"gpt-rosalind-research",
"gpt-live-1",
"gpt-5.5-cyber",
// Live model: Gemini Live uses a bidirectional API and is rejected by
// generateContent ("not supported for generateContent"), so it is not a
// chat/completions model. Excluded permanently (see PR that trimmed it from
Expand Down
Loading