codex-mini-latest retirement date: February 12, 2026
Retired on February 12, 2026; requests to codex-mini-latest now fail.
- Provider
- OpenAI
- Model IDs affected
codex-mini-latest- Announced
- November 17, 2025
- Shutdown date
- February 12, 2026
- Replacement
- gpt-5-codex-mini
- Platforms
- Dates apply to the OpenAI API. Fine-tuned models follow the same shutdown schedule as their base model. If you use OpenAI models through another platform, check that platform's own retirement schedule.
- Source
- Official OpenAI deprecations page (data last changed 2026-11-02, re-checked daily)
Migrating from codex-mini-latest
Not yet reviewed. We haven't written model-specific migration notes for codex-mini-latest yet. Start with the provider's official guidance and the replacement's model page, and use this general checklist:
- Search your code, config and environment variables for
codex-mini-latest. - Re-run your evaluation set against gpt-5-codex-mini before switching traffic.
- Recount tokens with the new model's tokenizer and re-check
max_tokens, context fit and cost. - Check tool calling, structured output and stop sequences on your real prompts.
- Dates apply to the OpenAI API. Fine-tuned models follow the same shutdown schedule as their base model. If you use OpenAI models through another platform, check that platform's own retirement schedule.
Check your code before Feb 12
All model retirements · All OpenAI deprecations
FAQ
When was codex-mini-latest retired?
codex-mini-latest (codex-mini-latest) was retired on the OpenAI API on February 12, 2026, according to the official OpenAI API deprecations page. Requests to it now fail.
What should I use instead of codex-mini-latest?
The recommended replacement is gpt-5-codex-mini.
What happens to codex-mini-latest requests after the shutdown date?
After a model is retired, API requests to it return an error. Move traffic to the replacement and test it on your own prompts before the date.
Does this date apply to Amazon Bedrock, Vertex AI or Azure?
Dates apply to the OpenAI API. Fine-tuned models follow the same shutdown schedule as their base model. If you use OpenAI models through another platform, check that platform’s own retirement schedule.