dall-e-2 retirement date: May 12, 2026
Retired on May 12, 2026; requests to dall-e-2 now fail.
- Provider
- OpenAI
- Model IDs affected
dall-e-2- Announced
- November 14, 2025
- Shutdown date
- May 12, 2026
- Replacement
- gpt-image-2, gpt-image-1, or gpt-image-1-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 dall-e-2
Not yet reviewed. We haven't written model-specific migration notes for dall-e-2 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
dall-e-2. - Re-run your evaluation set against gpt-image-2, gpt-image-1, or gpt-image-1-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 May 12
Also shutting down on May 12, 2026
- dall-e-3
dall-e-3
All model retirements · All OpenAI deprecations
FAQ
When was dall-e-2 retired?
dall-e-2 (dall-e-2) was retired on the OpenAI API on May 12, 2026, according to the official OpenAI API deprecations page. Requests to it now fail.
What should I use instead of dall-e-2?
The recommended replacement is gpt-image-2, gpt-image-1, or gpt-image-1-mini.
What happens to dall-e-2 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.