Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
https://api.deepseek.com/v1 deepseek-chat-v3-2 deepseek-chat (V3.2) is listed for chat workloads and supports a 128K context window.
Check DeepSeek's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We only found this deepseek-v3-2 listing on DeepSeek in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | deepseek-chat (V3.2) | Check provider | 128K | Native | Dynamic |
| Model | Provider | Context | Access |
|---|---|---|---|
| deepseek-reasoner (R1) | DeepSeek | 128K | Check provider |
deepseek-chat (V3.2) is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
deepseek-chat (V3.2) appears in the free model catalog for DeepSeek, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is deepseek-chat-v3-2.
The listed free tier limit is Dynamic. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 128K tokens with up to 8K output tokens.
deepseek-chat (V3.2) — free model from DeepSeek.
For API keys, setup steps, and provider-level limits, see the DeepSeek provider page.