LibreChat/packages/api/src/endpoints
Danny Avila 2e683f112b
🦘 fix: Skip OpenAI Model Fetch For User-Provided Keys (#13038)
* fix: skip OpenAI model fetch if using user-provided key

There was a check present (via `opts.userProvidedOpenAI`), but it wasn't
working because `loadDefaultModels()` doesn't provide that parameter. As a
result, the server would repeatedly try to request models from OpenAI and get
401 errors in return.

We now check the env var directly, which matches how
`getAnthropicModels()` works.

* chore: remove unused OpenAI model option

* fix: honor explicit OpenAI key for model fetch

* fix: fall back from empty OpenAI option key

---------

Co-authored-by: Dan Lew <daniel@mightyacorn.com>
2026-05-09 16:12:25 -04:00
..
anthropic 🧵 feat: Enable Anthropic Tool Argument Streaming (#12962) 2026-05-06 01:09:14 -04:00
bedrock 🧵 feat: Enable Anthropic Tool Argument Streaming (#12962) 2026-05-06 01:09:14 -04:00
config 🛟 fix: Summarization Provider misses vertexai + case-mismatched custom endpoints (#13025) 2026-05-08 18:52:01 -04:00
custom 🪟 feat: Add allowedAddresses Exemption List For SSRF-Guarded Targets (#12933) 2026-05-03 21:43:59 -04:00
google 🐛 fix: Propagate User Identity to Subagent MCP Tool Calls (#12950) 2026-05-05 12:19:50 +09:00
openai 🧭 feat: Add OpenRouter Prompt Cache Setting (#13029) 2026-05-09 11:46:09 -04:00
index.ts 🧵 refactor: Migrate Endpoint Initialization to TypeScript (#10794) 2025-12-11 16:37:16 -05:00
models.spec.ts 🦘 fix: Skip OpenAI Model Fetch For User-Provided Keys (#13038) 2026-05-09 16:12:25 -04:00
models.ts 🦘 fix: Skip OpenAI Model Fetch For User-Provided Keys (#13038) 2026-05-09 16:12:25 -04:00