Migrating off /v1/audio/translations — retirement date and replacement
Source last checked: 2026-10-19.
OpenAI is retiring /v1/audio/translations on 2027-02-26 — in 130 days. The provider’s documented replacement is v1/realtime/translations. This page is built from OpenAI’s official deprecation notice and is rechecked weekly; the source link is below.
When is /v1/audio/translations being deprecated?
| Model | Provider | Retires | Replacement |
|---|---|---|---|
| /v1/audio/translations | OpenAI | 2027-02-26 | v1/realtime/translations |
Source: OpenAI deprecation notice · announced 2026-08-26
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 /v1/audio/translations to?
OpenAI documents v1/realtime/translations 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) | 215 ms | 311 ms | 100% | 287 |
| Europe (Germany) | 291 ms | 401 ms | 100% | 288 |
| South America (São Paulo) | 252 ms | 496 ms | 100% | 287 |
| US (Central) | 138 ms | 211 ms | 100% | 287 |
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 2027-02-26?
| Model | Provider | Retires | Replacement |
|---|---|---|---|
| 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 |
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-4o | OpenAI | 2027-01-14 | gpt-6-luna |
| GPT-4o mini | OpenAI | 2027-01-14 | gpt-6-luna |
| GPT-4.1 | OpenAI | 2027-01-14 | gpt-6-luna |
| GPT-4.1 mini | OpenAI | 2027-01-14 | gpt-6-luna |
| gpt-5.3-codex | OpenAI | 2027-04-01 | gpt-6-sol |
| gpt-5.4-nano | OpenAI | 2027-04-01 | gpt-6-luna |
| gpt-5.1 | OpenAI | 2027-04-01 | gpt-6-sol |
| tts-1 | OpenAI | 2027-01-06 | gpt-realtime-2.1-mini |
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.