Looks like a leak: https://platform.openai.com/docs/models does not list it, and codex-mini-latest says that it's based on 4o. I wonder if it will be faster than codex; gpt-5-nano and -mini are still very slow for me on API, surprisingly so.
All "AI" providers cut corners in the models right now because the subsidized cost is unsustainable.
Grok's latest update made it far worse than the version right after the Grok-4 release. It makes outright mistakes now. Copilot has cut corners long ago. Google "AI" was always horrible.
The whole "AI" experiment was an outrageously expensive IP laundering parlor trick that is meeting economic realities now.
I had quite a fun time getting those pelicans though... since GPT-5 Codex Mini isn't officially available via API yet I instead had OpenAI's Codex CLI tool extend itself (in Rust) to add a "codex prompt ..." tool which uses their existing custom auth scheme and backend API, then used that to generate the pelicans. Full details here: https://simonwillison.net/2025/Nov/9/gpt-5-codex-mini/
Since they also limited the usage of codex CLI quite a bit, this might help. I really like the gpt-5-codex model. It has the most impressive dynamic reasoning effort I've seen. Responding instantly to simple questions while thinking very long when necessary. It's also interesting how close it is in many benchmarks to gpt-5. It's not just a good coding model. It's a great agentic model.
8 comments
[ 3.0 ms ] story [ 26.2 ms ] threadGrok's latest update made it far worse than the version right after the Grok-4 release. It makes outright mistakes now. Copilot has cut corners long ago. Google "AI" was always horrible.
The whole "AI" experiment was an outrageously expensive IP laundering parlor trick that is meeting economic realities now.
For comparison, here's GPT-5-Codex (not mini) https://static.simonwillison.net/static/2025/codex-hacking-d... and full GPT-5: https://static.simonwillison.net/static/2025/codex-hacking-g...
I had quite a fun time getting those pelicans though... since GPT-5 Codex Mini isn't officially available via API yet I instead had OpenAI's Codex CLI tool extend itself (in Rust) to add a "codex prompt ..." tool which uses their existing custom auth scheme and backend API, then used that to generate the pelicans. Full details here: https://simonwillison.net/2025/Nov/9/gpt-5-codex-mini/