Migrating off code-davinci-edit-001 — retirement date and replacement
Source last checked: 2026-09-15.
OpenAI is retiring code-davinci-edit-001 on 2024-01-04. The provider’s documented replacement is gpt-4o. This page is built from OpenAI’s official deprecation notice and is rechecked weekly; the source link is below.
Past scheduled retirement. The published shutdown date has passed; this is a historical notice, not a live availability check.
When is code-davinci-edit-001 being deprecated?
| Model | Provider | Retires | Replacement |
|---|---|---|---|
| code-davinci-edit-001 | OpenAI | 2024-01-04 | gpt-4o |
Source: OpenAI deprecation notice
Test before switching
- Check the replacement's supported API endpoints and request parameters.
- Test your prompts, structured output, streaming and tool calls on staging.
- Compare quality, latency, pricing and rate limits on your workload.
- Keep a rollback path while the old model remains available.
Download retirement dates for your models.
What should I migrate code-davinci-edit-001 to?
OpenAI documents gpt-4o as the successor. This is not a compatibility guarantee: request parameters, API endpoints, pricing, tool calls and output behaviour may differ. Check the linked provider documentation and run your own workload before switching.
Measured latency of the OpenAI API host
| Region | p50 TTFB | p95 | Uptime | Probes |
|---|---|---|---|---|
| Asia (Tokyo) | 201 ms | 291 ms | 100% | 288 |
| Europe (Germany) | 204 ms | 397 ms | 100% | 291 |
| South America (São Paulo) | 236 ms | 481 ms | 100% | 288 |
| US (Central) | 135 ms | 214 ms | 100% | 288 |
Edge latency to the provider’s API host over the last 24 hours, measured from 4 regions. This measures the endpoint, not the model: swapping models on the same host is not an inference benchmark or a promise about the replacement model. Compare edge latency →
What else retires on 2024-01-04?
| Model | Provider | Retires | Replacement |
|---|---|---|---|
| /v1/fine-tunes | OpenAI | 2024-01-04 | /v1/fine_tuning/jobs |
| text-ada-001 | OpenAI | 2024-01-04 | gpt-3.5-turbo-instruct |
| text-babbage-001 | OpenAI | 2024-01-04 | gpt-3.5-turbo-instruct |
| text-curie-001 | OpenAI | 2024-01-04 | gpt-3.5-turbo-instruct |
| text-davinci-001 | OpenAI | 2024-01-04 | gpt-3.5-turbo-instruct |
| text-davinci-002 | OpenAI | 2024-01-04 | gpt-3.5-turbo-instruct |
| text-davinci-003 | OpenAI | 2024-01-04 | gpt-3.5-turbo-instruct |
| ada | OpenAI | 2024-01-04 | babbage-002 |
| babbage | OpenAI | 2024-01-04 | babbage-002 |
| curie | OpenAI | 2024-01-04 | davinci-002 |
| davinci | OpenAI | 2024-01-04 | davinci-002, gpt-3.5-turbo, gpt-4o |
| text-davinci-edit-001 | OpenAI | 2024-01-04 | gpt-4o |
| /v1/edits | OpenAI | 2024-01-04 | /v1/chat/completions |
| text-similarity-ada-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-search-ada-doc-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-search-ada-query-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| code-search-ada-code-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| code-search-ada-text-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-similarity-babbage-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-search-babbage-doc-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-search-babbage-query-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| code-search-babbage-code-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| code-search-babbage-text-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-similarity-curie-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-search-curie-doc-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-search-curie-query-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-similarity-davinci-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-search-davinci-doc-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
| text-search-davinci-query-001 | OpenAI | 2024-01-04 | text-embedding-3-small |
Same shutdown date. If you call more than one of these, they are one migration, not several.
Other OpenAI models being retired
| Model | Provider | Retires | Replacement |
|---|---|---|---|
| gpt-5.4-cyber | OpenAI | 2026-10-01 | gpt-5.6-cyber |
| whisper-1 | OpenAI | 2027-02-26 | gpt-live-transcribe or gpt-transcribe |
| gpt-4o-transcribe | OpenAI | 2027-02-26 | gpt-live-transcribe or gpt-transcribe |
| gpt-4o-mini-transcribe | OpenAI | 2027-02-26 | gpt-live-transcribe or gpt-transcribe |
| gpt-4o-transcribe-diarize | OpenAI | 2027-02-26 | gpt-live-transcribe or gpt-transcribe |
| gpt-realtime | OpenAI | 2027-01-20 | gpt-realtime-2.1 |
| gpt-audio | OpenAI | 2027-01-20 | gpt-audio-1.5 |
| gpt-4o-audio | OpenAI | 2027-01-20 | gpt-audio-1.5 |
How is this calendar maintained?
Entries are pulled from provider documentation by an automated weekly job and every one carries a link to its source. Nothing is inferred from blog posts or social media. When a provider changes a date, the change appears here after the next run and is visible in the changelog. The full calendar across all providers is on the deprecations page, and this provider’s own list is at OpenAI deprecations.