Skip to content

chore: update model catalog from bot issues #1081

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

Open
github-actions wants to merge 1 commit into
base: main
Choose a base branch
from
+52 −11
Open

chore: update model catalog from bot issues #1081

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
6 changes: 5 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 @@ -763,7 +763,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"gpt-5.4-mini": ["openai", "azure", "openrouter"],
"gpt-5.4-nano": ["openai", "azure", "openrouter"],
"Qwen/Qwen3.7-Plus": ["together"],
"qwen/qwen3.6-27b": ["groq"],
"qwen/qwen3.6-27b": ["groq", "openrouter"],

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 8, 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.

P2 Badge Keep OpenRouter out of Qwen's direct mapping

This widens the direct endpoint mapping for a model that still has Groq as its native provider. The catalog sync code explicitly keeps OpenRouter aggregator unions out of direct index.ts endpoint types unless OpenRouter is the only provider (packages/proxy/scripts/sync_models.ts:1360-1366); otherwise getDirectModelEndpointTypes("qwen/qwen3.6-27b") starts offering OpenRouter routing/credential fallback instead of leaving this native model direct-routed to Groq. Keep openrouter in available_providers if desired, but don't add it to AvailableEndpointTypes here.

Useful? React with 👍 / 👎.

"gemini-3-pro-image": ["google"],
"publishers/google/models/gemini-3-pro-image": ["vertex"],
"claude-fable-5": ["anthropic"],
Expand Down Expand Up @@ -1350,6 +1350,10 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"databricks-claude-opus-5": ["databricks"],
"databricks-gemini-3-5-flash-lite": ["databricks"],
"accounts/fireworks/models/inkling": ["fireworks"],
"perplexity/kimi-k2.7-code": ["perplexity"],
"databricks-kimi-k3": ["databricks"],
"meta.llama4-scout-17b-instruct-v1:0": ["bedrock"],
"meta.llama4-maverick-17b-instruct-v1:0": ["bedrock"],
};

const modelEndpointAvailableModels = getAvailableModels();
Expand Down
57 changes: 47 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 @@ -5923,7 +5923,7 @@
"displayName": "Qwen 3.6 27B",
"experimental": true,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_output_tokens": 16384,
"available_providers": [
"groq",
"openrouter"
Expand Down Expand Up @@ -6508,6 +6508,7 @@
"multimodal": true,
"input_cost_per_mil_tokens": 0.3,
"output_cost_per_mil_tokens": 2.5,
"input_cache_read_cost_per_mil_tokens": 0.03,
"displayName": "Gemini 2.5 Flash",
"reasoning": true,
"reasoning_budget": true,
Expand Down Expand Up @@ -6555,6 +6556,7 @@
"multimodal": true,
"input_cost_per_mil_tokens": 1.25,
"output_cost_per_mil_tokens": 10,
"input_cache_read_cost_per_mil_tokens": 0.13,
"displayName": "Gemini 2.5 Pro",
"reasoning": true,
"reasoning_budget": true,
Expand Down Expand Up @@ -7947,15 +7949,21 @@
"multimodal": true,
"displayName": "Llama 4 Scout",
"max_input_tokens": 10000000,
"max_output_tokens": 8000
"max_output_tokens": 8000,
"available_providers": [
"bedrock"
]
},
"meta.llama4-maverick-17b-instruct-v1:0": {
"format": "converse",
"flavor": "chat",
"multimodal": true,
"displayName": "Llama 4 Maverick",
"max_input_tokens": 1000000,
"max_output_tokens": 8000
"max_output_tokens": 8000,
"available_providers": [
"bedrock"
]
},
"claude-fable-5": {
"format": "anthropic",
Expand Down Expand Up @@ -8462,10 +8470,10 @@
"format": "anthropic",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 3,
"output_cost_per_mil_tokens": 15,
"input_cache_read_cost_per_mil_tokens": 0.3,
"input_cache_write_cost_per_mil_tokens": 3.75,
"input_cost_per_mil_tokens": 6,
"output_cost_per_mil_tokens": 30,
"input_cache_read_cost_per_mil_tokens": 0.6,
"input_cache_write_cost_per_mil_tokens": 7.5,
"displayName": "Claude Sonnet 3.5 v2",
"max_input_tokens": 1000000,
"max_output_tokens": 8192,
Expand All @@ -8477,8 +8485,8 @@
"format": "anthropic",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 3,
"output_cost_per_mil_tokens": 15,
"input_cost_per_mil_tokens": 6,
"output_cost_per_mil_tokens": 30,
"input_cache_read_cost_per_mil_tokens": 0.3,
"input_cache_write_cost_per_mil_tokens": 3.75,
"displayName": "Claude Sonnet 3.5",
Expand Down Expand Up @@ -8562,6 +8570,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.14,
"output_cost_per_mil_tokens": 0.4,
"displayName": "Gemma 4 31B",
"reasoning": true,
"max_input_tokens": 256000,
Expand All @@ -8573,6 +8583,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.13,
"output_cost_per_mil_tokens": 0.4,
"displayName": "Gemma 4 26B A4B",
"reasoning": true,
"max_input_tokens": 256000,
Expand All @@ -8584,6 +8596,8 @@
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.04,
"output_cost_per_mil_tokens": 0.08,
"displayName": "Gemma 4 E2B",
"reasoning": true,
"max_input_tokens": 128000,
Expand Down Expand Up @@ -10907,7 +10921,7 @@
"output_cost_per_mil_tokens": 0.9,
"displayName": "Codestral 2508",
"parent": "codestral-latest",
"max_input_tokens": 256000,
"max_input_tokens": 128000,
"available_providers": [
"mistral",
"openrouter"
Expand Down Expand Up @@ -12936,6 +12950,17 @@
"databricks"
]
},
"databricks-kimi-k3": {

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 8, 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.

P2 Badge Add the missing Databricks GPT-5.4 Mini entry

The batch text says #1075 adds both databricks-kimi-k3 and databricks-gpt-5-4-mini, but only Kimi is introduced here; I checked the repo with rg 'databricks-gpt-5-4-mini' and there is still no model_list.json or AvailableEndpointTypes entry. In the scenario where this release is expected to expose the new Databricks GPT-5.4 Mini model, requests or selection for that ID will continue to fail as unknown even though the issue is closed.

Useful? React with 👍 / 👎.

"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "Kimi K3",
"reasoning": true,
"max_input_tokens": 1048576,
"available_providers": [
"databricks"
]
},
"gryphe/mythomax-l2-13b": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -13332,6 +13357,18 @@
"openrouter"
]
},
"perplexity/kimi-k2.7-code": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.95,
"output_cost_per_mil_tokens": 4,
"input_cache_read_cost_per_mil_tokens": 0.19,
"displayName": "Perplexity: Kimi K2.7 Code",
"max_input_tokens": 262144,
"available_providers": [
"perplexity"
]
},
"deepcogito/cogito-v2.1-671b": {
"format": "openai",
"flavor": "chat",
Expand Down