error: 413 Request body too large for gpt-4.1 model.

[ldennington]

I've been using the ai-inference action in one of my repos for about a month now. I use the same scenario repeatedly in my demos to show its capabilities:

1. Introduce a simple type error that will break CI builds.
2. Create a PR to trigger CI.
3. Wait for the failure to trigger my workflow that runs ai-inference.

Although this has worked in the past (using the same type error), I'm now getting the following issue from ai-inference:

413 Request body too large for gpt-4.1 model. Max size: 16000 tokens.

Note that I've made sure I'm using the latest version of the Action and updated to gpt-5 to see if that fixes the problem, but that model seems to have an even lower max size (4000 tokens).

Is anyone able to help me understand why this failure is happening/which model(s) may fix it?

[abhi-iac]

I have the exactly same error, I am trying the same use case but even my prompt has quite low token of context still encountering same issue.

413 Request body too large for gpt-4o model. Max size: 8000 tokens. Any help would appreciate.