Skip to content
Open
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
1 change: 1 addition & 0 deletions packages/proxy/schema/index.ts
Original file line number Diff line number Diff line change
Expand Up @@ -467,6 +467,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"fireworks_ai/accounts/fireworks/models/deepseek-v3p1": ["fireworks"],
"fireworks_ai/accounts/fireworks/models/firefunction-v2": ["fireworks"],
"fireworks_ai/accounts/fireworks/models/glm-4p5": ["fireworks"],
"fireworks_ai/accounts/fireworks/models/glm-5": ["fireworks"],
"fireworks_ai/accounts/fireworks/models/glm-4p5-air": ["fireworks"],
"fireworks_ai/accounts/fireworks/models/gpt-oss-120b": ["fireworks"],
"fireworks_ai/accounts/fireworks/models/gpt-oss-20b": ["fireworks"],
Expand Down
12 changes: 12 additions & 0 deletions packages/proxy/schema/model_list.json
Original file line number Diff line number Diff line change
Expand Up @@ -5879,6 +5879,18 @@
"fireworks"
]
},
"fireworks_ai/accounts/fireworks/models/glm-5": {
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 Register glm-5 in endpoint type map

This new model entry is only added to model_list.json, but getModelEndpointTypes in packages/proxy/schema/index.ts resolves provider routing from AvailableEndpointTypes first and otherwise falls back to DefaultEndpointTypes by format. Because fireworks_ai/accounts/fireworks/models/glm-5 is missing from that map (I checked the AvailableEndpointTypes block in index.ts), it will resolve to the OpenAI/Azure defaults instead of Fireworks, which can mis-route requests and select the wrong secret type whenever lookup falls back (for example in edge/index.ts when credential lookup fails).

Useful? React with 👍 / 👎.

"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 1,
"output_cost_per_mil_tokens": 3.2,
"max_input_tokens": 202752,
"max_output_tokens": 128000,
"reasoning": true,
"available_providers": [
"fireworks"
]
},
"accounts/fireworks/models/kimi-k2p5": {
"format": "openai",
"flavor": "chat",
Expand Down
Loading