text-embedding-004 deprecation — retirement date and replacement
Source last checked: 2026-11-08.
Google is retiring text-embedding-004 on 2026-01-14. The provider’s documented replacement is gemini-embedding-2. This page is built from Google’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 text-embedding-004 being deprecated?
| Model | Provider | Retires | Replacement |
|---|---|---|---|
| text-embedding-004 | 2026-01-14 | gemini-embedding-2 |
Source: Google 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 text-embedding-004 to?
Google documents gemini-embedding-2 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 Google API host
| Region | p50 TTFB | p95 | Uptime | Probes |
|---|---|---|---|---|
| Asia (Tokyo) | 63 ms | 118 ms | 100% | 287 |
| Europe (Germany) | 93 ms | 102 ms | 100% | 297 |
| South America (Santiago) | 972 ms | 1071 ms | 100% | 98 |
| US (Central) | 41 ms | 111 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
Other Google models being retired
| Model | Provider | Retires | Replacement |
|---|---|---|---|
| gemini-3.1-flash-lite | 2027-05-07 or later | gemini-3.5-flash-lite | |
| gemini-3.1-flash-tts-preview | 2026-11-17 or later | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | |
| gemini-3-pro-preview | 2026-03-09 | gemini-3.1-pro-preview | |
| gemini-3.1-flash-lite-preview | 2026-05-25 | gemini-3.1-flash-lite | |
| gemini-2.5-pro | 2026-12-01 | gemini-3.8-flash | |
| gemini-2.5-computer-use-preview-10-2025 | 2026-07-28 | gemini-3.8-flash | |
| gemini-2.5-pro-preview-03-25 | 2025-12-02 | gemini-3.8-flash | |
| gemini-2.5-pro-preview-05-06 | 2025-12-02 | gemini-3.8-flash |
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 Google deprecations.