[GH-ISSUE #2103] [BUG]: gpt-4o-mini has a small prompt window limit #1371

Closed
opened 2026-02-22 18:24:29 -05:00 by yindo · 0 comments
Owner

Originally created by @mPyKen on GitHub (Aug 13, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2103

How are you running AnythingLLM?

Docker (remote machine)

What happened?

Prompt got cannonballed when using gpt-4o-mini at roughly 5k tokens.

Are there known steps to reproduce?

OpenAI's gpt-4o-mini model gets limited to a context size of 4096 although the actual limit is 128k.
https://github.com/Mintplex-Labs/anything-llm/blob/dfb951e9cf278e06273e9d0ccae1f4cca537fc2e/server/utils/AiProviders/openAi/index.js#L41-L58

Originally created by @mPyKen on GitHub (Aug 13, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2103 ### How are you running AnythingLLM? Docker (remote machine) ### What happened? Prompt got cannonballed when using gpt-4o-mini at roughly 5k tokens. ### Are there known steps to reproduce? OpenAI's gpt-4o-mini model gets limited to a context size of 4096 although the actual limit is 128k. https://github.com/Mintplex-Labs/anything-llm/blob/dfb951e9cf278e06273e9d0ccae1f4cca537fc2e/server/utils/AiProviders/openAi/index.js#L41-L58
yindo added the possible bug label 2026-02-22 18:24:29 -05:00
yindo closed this issue 2026-02-22 18:24:29 -05:00
yindo changed title from [BUG]: gpt-4o-mini has a small prompt window limit to [GH-ISSUE #2103] [BUG]: gpt-4o-mini has a small prompt window limit 2026-06-05 14:40:24 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1371