DeepSeek V3.2 with zero data retention.
DeepSeek's efficient model with sparse attention for reasoning and tools. On Thinkr, it runs with zero data retention (ZDR), so the provider keeps nothing.
›open/deepseek-v3.2
- Maker
- DeepSeek
- Feature
- Chat
- ZDR
- $0.24 in / $0.36 out per 1M tokens
- Context
- 164K tokens
Who can read it.
In ZDR and Open, Thinkr's proxy can read the chat in transit and writes none of it to disk.
More from DeepSeek.
- DeepSeek V4.1 FlashDeepSeek's fast open-weight model, with a long context and image input.See the model
- DeepSeek V4 Flash Vision ExpAn experimental V4 Flash from DeepSeek that also reads images.See the model
- DeepSeek V4 ProDeepSeek's large V4 model, with 1.6T parameters, for advanced reasoning.See the model