GPT-4o (2024-05-13) retirement date: October 23, 2026
Retired on October 23, 2026; requests to gpt-4o-2024-05-13 now fail.
- Provider
- OpenAI
- Model IDs affected
gpt-4o-2024-05-13- Announced
- April 22, 2026
- Shutdown date
- October 23, 2026
- Replacement
- gpt-5.6-sol
- 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)
GPT-4o (2024-05-13) vs GPT-5.6 Sol: price and limits
| GPT-4o (2024-05-13) | GPT-5.6 Sol | Change | |
|---|---|---|---|
| Context window (tokens) | 128,000 | 1,050,000 | +720% |
| Max output (tokens) | 4,096 | 128,000 | +3,025% |
| Input, $ per 1M tokens | $5.00 | $4.00 | -20% |
| Output, $ per 1M tokens | $15.00 | $20.00 | +33% |
| Cache read, $ per 1M tokens | — | $0.40 | — |
Prices and limits from models.dev (checked 2026-11-02). Confirm on the official pricing page. Compare the cost for your traffic in the old vs new model calculator.
Migrating from GPT-4o (2024-05-13) to GPT-5.6 Sol
Not yet reviewed. We haven't written model-specific migration notes for GPT-4o (2024-05-13) 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
gpt-4o-2024-05-13. - Re-run your evaluation set against gpt-5.6-sol 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 Oct 23
Also shutting down on October 23, 2026
- deep-research-pro-preview-12-2025
deep-research-pro-preview-12-2025 - ft-o4-mini
ft-o4-mini-2025-04-16 - GPT-3.5-turbo
gpt-3.5-turbo-0125 - GPT-4
gpt-4-0613 - GPT-4.1 nano
gpt-4.1-nano - GPT-4 1106 preview
gpt-4-1106-preview - GPT-4 Turbo
gpt-4-turbo - gpt-image-1
gpt-image-1 - o1
o1-2024-12-17 - o1-pro
o1-pro-2025-03-19 - o3-mini
o3-mini-2025-01-31 - o4-mini
o4-mini-2025-04-16
All model retirements · All OpenAI deprecations
FAQ
When was GPT-4o (2024-05-13) retired?
GPT-4o (2024-05-13) (gpt-4o-2024-05-13) was retired on the OpenAI API on October 23, 2026, according to the official OpenAI API deprecations page. Requests to it now fail.
What should I use instead of gpt-4o-2024-05-13?
The recommended replacement is gpt-5.6-sol.
What happens to gpt-4o-2024-05-13 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.