Model retirement dates / DeepSeek
deepseek-v4-flash
DeepSeek retired deepseek-v4-flash on 10 September 2026. Calls to it still work: DeepSeek answers them with deepseek-flash, so the model behind it changed. 'temporarily routed' to V4.1 Flash; the routing can end without a fixed date.
| Provider | DeepSeek |
|---|---|
| Model | deepseek-v4-flash |
| Status | Redirected to a newer model (as of 14 Nov 2026) |
| Redirect starts | 10 September 2026 |
| Now answered by | deepseek-flash |
| Model type | Text |
| Source | DeepSeek: news and updates (no deprecation page; read from announcements) |
Check your code for it
Run this in your repository. No install and no API key; it lists every OpenAI, Anthropic, Google, Mistral, xAI, Cohere, DeepSeek, Groq, Bedrock, Vertex AI and Azure model ID it finds, with its retirement date and replacement:
npx -y @aidriftline/driftline .
Or look for this ID only: grep -rn "deepseek-v4-flash" . (misses aliases, Bedrock and Vertex names, and IDs split across lines).
To be warned automatically before the next retirement, add the free Driftline GitHub Action. It annotates the exact line in pull requests and can fail the build on retired models.
Where a new name is the whole change, Driftline can make it for you: npx -y @aidriftline/driftline fix --dry-run shows the edits, and the Action's fix-pr: true opens one pull request with them, plus a checklist for the lines that need more. See an example pull request.
Same date at DeepSeek
Read from DeepSeek's official announcements on 14 November 2026, checked daily. Something wrong? hello@aidriftline.com