As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/deepseek-v3-2/

# DeepSeek-V3.2

DeepSeek, DeepSeek V3 family. Status: legacy. Type: reasoning model. Released: 2025-12-01. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| DeepSeek API (retired) | `deepseek-chat / deepseek-reasoner (no longer serve V3.2)` | https://api.deepseek.com | https://api-docs.deepseek.com/updates |
| OpenRouter | `deepseek/deepseek-v3.2` |  | https://openrouter.ai/deepseek/deepseek-v3.2 |
| Hugging Face |  |  | https://huggingface.co/deepseek-ai/DeepSeek-V3.2 |
| Hugging Face (Speciale) |  |  | https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text
- Output: text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: mit

## What it has not seen

- No published training cutoff. Counted from its release (2025-12-01): at least 1,968 AI events since (450 major, 85 historic), as of 2026-11-13.
- Everything since November 2025: https://postcutoff.com/since/2025-11/

## What stands out

- DeepSeek Sparse Attention (DSA): Introduced DSA (first in V3.2-Exp) to cut long-context attention compute while preserving quality. Source: https://huggingface.co/deepseek-ai/DeepSeek-V3.2
- Hybrid thinking/non-thinking in one model: deepseek-chat mapped to non-thinking mode and deepseek-reasoner to thinking mode of the same V3.2 weights. Source: https://api-docs.deepseek.com/updates
- V3.2-Speciale reasoning variant: Separate high-compute Speciale variant served briefly on a temporary endpoint (no tool calls) until 2025-12-15; weights released. Source: https://api-docs.deepseek.com/updates

## Notes

API aliases deepseek-chat/deepseek-reasoner moved to V4-Flash on 2026-04-24 and were scheduled for discontinuation on 2026-07-24; V3.2 now only via open weights/third parties. Pricing not verified (no first-party price).

Open-weight (MIT) predecessor of V4; still widely self-hosted and on third-party APIs. Use deepseek-v4-pro / deepseek-flash on the first-party API instead.

Sources: https://api-docs.deepseek.com/updates · https://huggingface.co/deepseek-ai/DeepSeek-V3.2 · https://openrouter.ai/deepseek/deepseek-v3.2

Model page: https://postcutoff.com/m/deepseek-v3-2/