# DeepSeek Reasoner — deprecation status

> Yes — DeepSeek Reasoner is retired. DeepSeek deprecated it on April 24, 2026 and shut it down on July 24, 2026; API requests to it now fail. The recommended replacement is DeepSeek V4 Flash.

The id that served DeepSeek-R1 in January 2025, the open-weights reasoning model that made chain-of-thought cheap and briefly moved the US stock market. It was the first mainstream API to hand back the reasoning trace itself in `reasoning_content`. From V3.1 onwards it stopped being a separate model and became the thinking half of a hybrid one, which is why V4 replaced it with a request parameter rather than another id.

## Facts

| Field | Value |
| --- | --- |
| Provider | DeepSeek |
| Model id | `deepseek-reasoner` |
| Status | Retired |
| Released | January 20, 2025 |
| Deprecated | April 24, 2026 |
| Shutdown | July 24, 2026 (10 days ago) |
| Last verified | August 3, 2026 |

## Replacement

- **DeepSeek V4 Flash** (`deepseek-v4-flash`) · recommended — https://modeldeprecations.dev/deepseek/deepseek-v4-flash
  - deepseek-reasoner routed to V4-Flash with thinking on, which is the default, so `model: "deepseek-v4-flash"` reproduces the old behaviour. Use `thinking.reasoning_effort` (`low`, `high`, `max`) to trade depth against cost, and deepseek-v4-pro for the hardest problems.
  - Parameters it accepts: https://modelparams.dev/models/deepseek/deepseek-v4-flash

```diff
- "model": "deepseek-reasoner"
+ "model": "deepseek-v4-flash"
```

## FAQ

### When did DeepSeek Reasoner shut down?

DeepSeek Reasoner shut down on July 24, 2026. API requests to it fail from that date onward.

### What replaces DeepSeek Reasoner?

DeepSeek recommends DeepSeek V4 Flash (`deepseek-v4-flash`) as the replacement for DeepSeek Reasoner. deepseek-reasoner routed to V4-Flash with thinking on, which is the default, so `model: "deepseek-v4-flash"` reproduces the old behaviour. Use `thinking.reasoning_effort` (`low`, `high`, `max`) to trade depth against cost, and deepseek-v4-pro for the hardest problems.

### Is DeepSeek Reasoner still available?

No. DeepSeek Reasoner is retired and no longer served — it was shut down on July 24, 2026. Calls to it return an error.

### How do I migrate from DeepSeek Reasoner to deepseek-v4-flash?

Swap the model id in your API call: replace "deepseek-reasoner" with "deepseek-v4-flash". deepseek-reasoner routed to V4-Flash with thinking on, which is the default, so `model: "deepseek-v4-flash"` reproduces the old behaviour. Use `thinking.reasoning_effort` (`low`, `high`, `max`) to trade depth against cost, and deepseek-v4-pro for the hardest problems.

## Sources

- [DeepSeek-R1 Release](https://api-docs.deepseek.com/news/news250120/) — accessed 2026-08-03
- [DeepSeek V4 Preview Release](https://api-docs.deepseek.com/news/news260424/) — accessed 2026-08-03
- [DeepSeek API change log](https://api-docs.deepseek.com/updates/) — accessed 2026-08-03

---

Canonical page: https://modeldeprecations.dev/deepseek/deepseek-reasoner
JSON: https://modeldeprecations.dev/api/v1/models/deepseek/deepseek-reasoner.json