O1-Mini & O3-Mini rejected the request

[ramifara]

What happened?

When trying to use any version of O1-Mini & O3-Mini I get the error in the screenshot below:

I have checked with OpenAI and I have access to those models

Version Information

ghcr.io/danny-avila/librechat-dev-api latest 5c28cb2558cc 12 hours ago 989MB
ghcr.io/danny-avila/librechat-rag-api-dev-lite latest 1ae8fe67976f 10 months ago 1.51GB

Steps to Reproduce

Choose any o1-mini/o3-mini models
send any requests

What browsers are you seeing the problem on?

Chrome

Relevant log output

{"code":"unsupported_value","error":{"code":"unsupported_value","message":"Unsupported value: 'temperature' does not support 0.94 with this model. Only the default (1) value is supported.","param":"temperature","type":"invalid_request_error"},"headers":{"access-control-expose-headers":"X-Request-ID","alt-svc":"h3=\":443\"; ma=86400","cf-cache-status":"DYNAMIC","cf-ray":"910cd1712a831c3a-FRA","connection":"keep-alive","content-length":"248","content-type":"application/json","date":"Wed, 12 Feb 2025 13:10:19 GMT","openai-organization":"user-q5qhm5ep2lruqjbccgtqu9zb","openai-processing-ms":"19","openai-version":"2020-10-01","server":"cloudflare","set-cookie":"__cf_bm=.wz79bEMrZRnQhJt6FxW4bcFTj3fUHLsKaykrnHGnBU-1739365819-1.0.1.1-B7PZJWFhxqt3NoTyFDaZi.Vb4IejKa1JlcMsZJyibtOTnbMhJd5s2Mzw6UwvgJh25achzIRoNoBp6L5Nva2zwQ; path=/; expires=Wed, 12-Feb-25 13:40:19 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None, _cfuvid=pEPzIU2l0DQvyqFdCWhbclh4tc9pHM9m_KhFkzxC3Wc-1739365819295-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None","strict-transport-security":"max-age=31536000; includeSubDomains; preload","x-content-type-options":"nosniff","x-ratelimit-limit-requests":"5000","x-ratelimit-limit-tokens":"4000000","x-ratelimit-remaining-requests":"4999","x-ratelimit-remaining-tokens":"3999711","x-ratelimit-reset-requests":"12ms","x-ratelimit-reset-tokens":"4ms","x-request-id":"req_d644e9ccc75376ebc2d8e7ef56020a68"},"level":"error","param":"temperature","request_id":"req_d644e9ccc75376ebc2d8e7ef56020a68","status":400,"type":"invalid_request_error"}
{"code":"unsupported_value","error":{"code":"unsupported_value","message":"Unsupported value: 'temperature' does not support 0.94 with this model. Only the default (1) value is supported.","param":"temperature","type":"invalid_request_error"},"headers":{"access-control-expose-headers":"X-Request-ID","alt-svc":"h3=\":443\"; ma=86400","cf-cache-status":"DYNAMIC","cf-ray":"910cd1712a831c3a-FRA","connection":"keep-alive","content-length":"248","content-type":"application/json","date":"Wed, 12 Feb 2025 13:10:19 GMT","openai-organization":"user-q5qhm5ep2lruqjbccgtqu9zb","openai-processing-ms":"19","openai-version":"2020-10-01","server":"cloudflare","set-cookie":"__cf_bm=.wz79bEMrZRnQhJt6FxW4bcFTj3fUHLsKaykrnHGnBU-1739365819-1.0.1.1-B7PZJWFhxqt3NoTyFDaZi.Vb4IejKa1JlcMsZJyibtOTnbMhJd5s2Mzw6UwvgJh25achzIRoNoBp6L5Nva2zwQ; path=/; expires=Wed, 12-Feb-25 13:40:19 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None, _cfuvid=pEPzIU2l0DQvyqFdCWhbclh4tc9pHM9m_KhFkzxC3Wc-1739365819295-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None","strict-transport-security":"max-age=31536000; includeSubDomains; preload","x-content-type-options":"nosniff","x-ratelimit-limit-requests":"5000","x-ratelimit-limit-tokens":"4000000","x-ratelimit-remaining-requests":"4999","x-ratelimit-remaining-tokens":"3999711","x-ratelimit-reset-requests":"12ms","x-ratelimit-reset-tokens":"4ms","x-request-id":"req_d644e9ccc75376ebc2d8e7ef56020a68"},"level":"error","param":"temperature","request_id":"req_d644e9ccc75376ebc2d8e7ef56020a68","status":400,"type":"invalid_request_error"}

Screenshots

No response

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

Can’t reproduce, no relevant log output provided, can’t help.

[ramifara]

Sorry I might have missed it in the Bug template, but which relevant log was needed? I will provide it

[danny-avila]

The issue template has instructions, please revisit them

[ramifara]

I have added the logs for the times it happened to the discussion , sorry I missed it at first!

[ramifara]

okay as instructed in the logs setting the temperature to 1 fixed my issue. Maybe there is need for adding a check in the code so this will be done automatically, or this message could be send back to the users.

[ramifara]

the problem was caused by using my presets and only changing the model. I am sure this will happen with other users too

[philipbrembeck]

There's a way in LibreChat to drop certain parameters.

E.g. for o3-mini:

          - group: "openai-models"
            ...
            dropParams: ["stream", "temperature", "top_p", "presence_penalty", "frequency_penalty", "best_of", "max_tokens", "stop"]
           ...