Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -1438,6 +1438,9 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"mistral.voxtral-mini-3b-2507": ["bedrock"],
"mistral.voxtral-small-24b-2507": ["bedrock"],
"global.anthropic.claude-mythos-5": ["bedrock"],
"databricks-gpt-6-astra": ["databricks"],
"databricks-glm-5-3": ["databricks"],
"databricks-deepseek-v4-1-flash": ["databricks"],
Comment on lines +1441 to +1443

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 Remove routing edits from the deprecated proxy

These AvailableEndpointTypes entries are model-routing configuration in the deprecated proxy, so they update the wrong implementation and will not configure the active gateway. Keep the valid catalog additions in model_list.json, but move any required Databricks routing work to the parent repository's gateway/ directory as required by the repository instructions.

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

Useful? React with 👍 / 👎.

};

const modelEndpointAvailableModels = getAvailableModels();
Expand Down
60 changes: 47 additions & 13 deletions packages/proxy/schema/model_list.json
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 @@ -13383,6 +13370,40 @@
"openrouter"
]
},
"databricks-deepseek-v4-1-flash": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "DeepSeek V4.1 Flash",
"reasoning": true,
"max_input_tokens": 1048576,
"available_providers": [
"databricks"
]
},
"databricks-glm-5-3": {
"format": "openai",
"flavor": "chat",
"displayName": "GLM 5.3",
"reasoning": true,
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"available_providers": [
"databricks"
]
},
"databricks-gpt-6-astra": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "GPT-6 Astra",
"reasoning": true,
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"available_providers": [
"databricks"
]
},
"databricks-gemini-3-8-flash": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -14192,6 +14213,19 @@
"typesafe"
]
},
"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"
]
},
"unbiased/pareto": {
"format": "openai",
"flavor": "chat",
Expand Down