Skip to content

chore: sync new models #1273

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

Closed
github-actions wants to merge 1 commit into from
+94 −44
Closed

chore: sync new models #1273

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
4 changes: 4 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 @@ -400,6 +400,8 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"mixtral-8x7b": ["lepton"],
"wizardlm-2-7b": ["lepton"],
"wizardlm-2-8x22b": ["lepton", "openrouter"],
"prism-ml/ternary-bonsai-2-27b": ["openrouter"],
"z-ai/glm-5.3-flashx": ["openrouter"],
"unbiased/pareto": ["openrouter"],
"inference-net/schematron-v2-turbo": ["openrouter"],
"inference-net/schematron-v2-small": ["openrouter"],
Expand Down Expand Up @@ -1184,6 +1186,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"grok-3-mini": ["xAI"],
"grok-3-mini-latest": ["xAI"],
"grok-imagine-image-2.0": ["xAI"],
"grok-voice-transcribe-2.0": ["xAI"],
"grok-imagine-video-1.5": ["xAI"],
"grok-imagine-video-1.5-preview": ["xAI"],
"grok-imagine-video-1.5-2026-05-30": ["xAI"],
Expand All @@ -1192,6 +1195,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"grok-3-mini-beta": ["xAI"],
"grok-3-mini-fast-beta": ["xAI"],
"grok-code-fast-1": ["xAI"],
"grok-voice-transcribe-1.0": ["xAI"],
"grok-code-fast": ["xAI"],
"grok-imagine-image": ["xAI"],
"grok-imagine-image-quality": ["xAI"],
Expand Down
134 changes: 90 additions & 44 deletions packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6399,19 +6399,6 @@
"openrouter"
]
},
"qwen/qwen3.6-27b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.6,
"output_cost_per_mil_tokens": 3,
"displayName": "Qwen 3.6 27B",
"experimental": true,
"max_input_tokens": 131072,
"max_output_tokens": 16384,
"available_providers": [
"openrouter"
]
},
"groq/compound": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -12617,6 +12604,22 @@
"vertex"
]
},
"grok-voice-transcribe-1.0": {
"format": "openai",
"flavor": "chat",

@chatgpt-codex-connector chatgpt-codex-connector Bot Sep 19, 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 Exclude transcription-only models from the chat catalog

When either new grok-voice-transcribe-* ID is selected through /auto, this chat flavor makes packages/proxy/src/proxy.ts route it to /chat/completions, although the repository's NON_CHAT_MODEL_PATTERN explicitly classifies -transcribe models as unsuitable for chat probing and this proxy has no audio-transcription route. Both entries will therefore advertise an xAI model that cannot be invoked through the supported path; remove them until the corresponding transcription routing is implemented in the parent gateway.

AGENTS.md reference: AGENTS.md:L6-L8

Useful? React with 👍 / 👎.

"displayName": "Grok Voice Transcribe 1.0",
"available_providers": [
"xAI"
]
},
"grok-voice-transcribe-2.0": {
"format": "openai",
"flavor": "chat",
"displayName": "Grok Voice Transcribe 2.0",
"available_providers": [
"xAI"
]
},
"grok-imagine-video": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -14192,6 +14195,34 @@
"typesafe"
]
},
"prism-ml/ternary-bonsai-2-27b": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.075,
"output_cost_per_mil_tokens": 0.5,
"displayName": "PrismML: Ternary Bonsai 2 27B",
"reasoning": true,
"max_input_tokens": 262144,
"max_output_tokens": 32768,
"available_providers": [
"openrouter"
]
},
"qwen/qwen3.6-27b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.3,
"output_cost_per_mil_tokens": 2,
"input_cache_read_cost_per_mil_tokens": 0.03,
"displayName": "Qwen: Qwen3.6 27B",
"experimental": true,
"max_input_tokens": 131072,
"max_output_tokens": 16384,
"available_providers": [
"openrouter"
]
},
"unbiased/pareto": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -14358,8 +14389,8 @@
"meta-llama/llama-3.1-70b-instruct": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.4,
"output_cost_per_mil_tokens": 0.4,
"input_cost_per_mil_tokens": 0.72,
"output_cost_per_mil_tokens": 0.72,
"displayName": "Meta: Llama 3.1 70B Instruct",
"max_input_tokens": 131072,
"max_output_tokens": 16384,
Expand Down Expand Up @@ -14422,8 +14453,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.1875,
"output_cost_per_mil_tokens": 0.6525,
"input_cost_per_mil_tokens": 0.2,
"output_cost_per_mil_tokens": 0.8,
"displayName": "Meta: Llama 4 Maverick",
"max_input_tokens": 1048576,
"max_output_tokens": 16384,
Expand Down Expand Up @@ -14826,7 +14857,7 @@
"nvidia/nemotron-3.5-lightning": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.08,
"input_cost_per_mil_tokens": 0.07,
"output_cost_per_mil_tokens": 0.2,
"input_cache_read_cost_per_mil_tokens": 0.04,
"displayName": "NVIDIA: Nemotron 3.5 Lightning",
Expand Down Expand Up @@ -14954,9 +14985,9 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.2156,
"output_cost_per_mil_tokens": 0.6468,
"input_cache_read_cost_per_mil_tokens": 0.00686,
"input_cost_per_mil_tokens": 0.22,
"output_cost_per_mil_tokens": 0.66,
"input_cache_read_cost_per_mil_tokens": 0.007,
"displayName": "DeepSeek: DeepSeek V4 Flash Vision Exp",
"reasoning": true,
"max_input_tokens": 1048576,
Expand All @@ -14983,9 +15014,9 @@
"deepseek/deepseek-v4-flash-0731": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.06,
"output_cost_per_mil_tokens": 0.12,
"input_cache_read_cost_per_mil_tokens": 0.012,
"input_cost_per_mil_tokens": 0.04,
"output_cost_per_mil_tokens": 0.16,
"input_cache_read_cost_per_mil_tokens": 0.016,
"displayName": "DeepSeek: DeepSeek V4 Flash (0731)",
"reasoning": true,
"parent": "deepseek/deepseek-v4-flash",
Expand Down Expand Up @@ -15121,9 +15152,9 @@
"deepseek/deepseek-v4-pro": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 1.6,
"output_cost_per_mil_tokens": 3.2,
"input_cache_read_cost_per_mil_tokens": 0.135,
"input_cost_per_mil_tokens": 0.95526,
"output_cost_per_mil_tokens": 1.91052,
"input_cache_read_cost_per_mil_tokens": 0.079605,
"displayName": "DeepSeek: DeepSeek V4 Pro",
"reasoning": true,
"max_input_tokens": 1048576,
Expand Down Expand Up @@ -15271,9 +15302,9 @@
"ibm-granite/granite-4.2-8b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.06,
"output_cost_per_mil_tokens": 0.25,
"input_cache_read_cost_per_mil_tokens": 0.015,
"input_cost_per_mil_tokens": 0.1,
"output_cost_per_mil_tokens": 0.15,
"input_cache_read_cost_per_mil_tokens": 0.05,
"displayName": "IBM: Granite 4.2 8B",
"reasoning": true,
"max_input_tokens": 131072,
Expand Down Expand Up @@ -15489,6 +15520,21 @@
"openrouter"
]
},
"z-ai/glm-5.3-flashx": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.37,
"output_cost_per_mil_tokens": 1.25,
"input_cache_read_cost_per_mil_tokens": 0.075,
"displayName": "Z.ai: GLM 5.3 FlashX",
"reasoning": true,
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"available_providers": [
"openrouter"
]
},
"z-ai/glm-5.3-flash": {
"format": "openai",
"flavor": "chat",
Expand All @@ -15507,9 +15553,9 @@
"z-ai/glm-5.3": {
"format": "openai",
"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_cost_per_mil_tokens": 0.91,
"output_cost_per_mil_tokens": 2.86,
"input_cache_read_cost_per_mil_tokens": 0.169,
"displayName": "Z.ai: GLM 5.3",
"reasoning": true,
"max_input_tokens": 1048576,
Expand Down Expand Up @@ -15678,9 +15724,9 @@
"z-ai/glm-5.2": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.5625,
"output_cost_per_mil_tokens": 1.8,
"input_cache_read_cost_per_mil_tokens": 0.105,
"input_cost_per_mil_tokens": 0.6496,
"output_cost_per_mil_tokens": 2.0416,
"input_cache_read_cost_per_mil_tokens": 0.12064,
"displayName": "Z.ai: GLM 5.2",
"reasoning": true,
"max_input_tokens": 1048576,
Expand Down Expand Up @@ -16137,7 +16183,7 @@
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.3,
"output_cost_per_mil_tokens": 1.1,
"output_cost_per_mil_tokens": 1.2,
"input_cache_read_cost_per_mil_tokens": 0.04,
"displayName": "Meta: Muse Glimmer 30B",
"reasoning": true,
Expand Down Expand Up @@ -16261,9 +16307,9 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 2.1,
"output_cost_per_mil_tokens": 10.95,
"input_cache_read_cost_per_mil_tokens": 0.23,
"input_cost_per_mil_tokens": 1.7,
"output_cost_per_mil_tokens": 8.5,
"input_cache_read_cost_per_mil_tokens": 0.17,
"displayName": "MoonshotAI: Kimi K3",
"reasoning": true,
"max_input_tokens": 1048576,
Expand Down Expand Up @@ -17072,8 +17118,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.1625,
"output_cost_per_mil_tokens": 1.3,
"input_cost_per_mil_tokens": 0.3125,
"output_cost_per_mil_tokens": 1.25,
"input_cache_read_cost_per_mil_tokens": 0.15625,
"displayName": "Qwen: Qwen3.5 35B A3B",
"reasoning": true,
Expand Down Expand Up @@ -17128,8 +17174,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.1,
"output_cost_per_mil_tokens": 0.9,
"input_cost_per_mil_tokens": 0.15,
"output_cost_per_mil_tokens": 1,
"input_cache_read_cost_per_mil_tokens": 0.05,
"displayName": "Qwen: Qwen3.6 35B A3B",
"reasoning": true,
Expand Down