Batch API for GPT 4o mini throwing a error 403

I get an error saying the model gpt-4o-mini-2024-07-18-batch is not found when i made a batch api request. I currently have


models accessible in my project. Can someone help me?

{“id”: “batch_req_6795506add2c8190ba2c494xxxxxxxx”, “custom_id”: “task-0”, “response”: {“status_code”: 403, “request_id”: “90e33ffbefba1ba4eabfc54xxxxxx”, “body”: {“error”: {“message”: “Project proj_LnTPIS8SfOKROL2xxxxxx does not have access to model gpt-4o-mini-2024-07-18-batch”, “type”: “invalid_request_error”, “param”: null, “code”: “model_not_found”}}}, “error”: null}

There is no “batch” model. This is OpenAI screwing up with the same symptom as has been seen before.

You can try both the gpt-4o-mini name and the dated version.

There is probably some backend translation of the name you use to the one that gives a discount internally, and it is either something about the project or something about the batch API.

You can try making a new API key or new project, and see if your rights to some secret model alias you can’t call directly is turned on.

2 Likes