Skip to content

chore: update model catalog from bot issues #1235

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 1 commit into from
Sep 11, 2026
Merged

chore: update model catalog from bot issues #1235

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
3 changes: 2 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 @@ -229,7 +229,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"gpt-4o-transcribe": ["openai", "azure"],
"gpt-4o-transcribe-diarize": ["openai", "azure"],
sonar: ["perplexity", "openrouter"],
"deepseek-ai/DeepSeek-V4.1-Flash": ["baseten"],
"deepseek-ai/DeepSeek-V4.1-Flash": ["baseten", "fireworks"],

@chatgpt-codex-connector chatgpt-codex-connector Bot Sep 11, 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 Do not route the Baseten model ID directly to Fireworks

When a request uses deepseek-ai/DeepSeek-V4.1-Flash and a Fireworks credential is selected, this mapping makes Fireworks eligible, but fetchOpenAI forwards bodyData.model unchanged for Fireworks. The request therefore sends the Baseten-style ID instead of the Fireworks inference ID added by this same commit, accounts/fireworks/models/deepseek-v4p1-flash, causing a model-not-found response. Keep Fireworks attached only to the provider-specific ID unless the routing layer translates between these IDs.

Useful? React with 👍 / 👎.

"deepseek-ai/DeepSeek-V4-Flash-0731": ["baseten", "together"],
"sonar-pro": ["perplexity", "openrouter"],
"sonar-reasoning-pro": ["perplexity", "openrouter"],
Expand Down Expand Up @@ -1428,6 +1428,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"qwen-3.8-27b": ["cerebras"],
"anthropic.claude-mythos-5-1": ["bedrock"],
"global.anthropic.claude-mythos-5-1": ["bedrock"],
"accounts/fireworks/models/deepseek-v4p1-flash": ["fireworks"],
};

const modelEndpointAvailableModels = getAvailableModels();
Expand Down
17 changes: 16 additions & 1 deletion packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2947,6 +2947,20 @@
"azure"
]
},
"accounts/fireworks/models/deepseek-v4p1-flash": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"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 V4.1 Flash",
"reasoning": true,
"max_input_tokens": 1048576,
"available_providers": [
"fireworks"
]
},
"accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -11245,7 +11259,8 @@
"reasoning": true,
"max_input_tokens": 1048576,
"available_providers": [
"baseten"
"baseten",
"fireworks"
]
},
"deepseek-ai/DeepSeek-V4-Flash-0731": {
Expand Down