DeepSeek V3.2 Thinking
DeepSeek‑V3.2 from DeepSeek harmonizes high computational efficiency with superior reasoning and agent performance. It builds on three main techniques: DeepSeek Sparse Attention for long‑context effi…
vercelAIGatewayCatalog/deepseek/deepseek-v3.2-thinking
DeepSeek‑V3.2 from DeepSeek harmonizes high computational efficiency with superior reasoning and agent performance. It builds on three main techniques: DeepSeek Sparse Attention for long‑context efficiency, a scalable reinforcement learning framework, and a large‑scale agentic task synthesis pipeline. This model excels at long-context reasoning and agentic tasks, efficiently handling extended inputs while maintaining strong accuracy. Its sparse attention design enables it to process complex, multi-step workflows without excessive compute costs. Overall, DeepSeek‑V3.2 targets long‑context reasoning, tool‑using agents, and efficient deployment in production environments.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 128000
- Max output · tokens
- 8000
Safety assessments
1–1 / 1
32 / 100
- source id
- stanfordFMTI
- canonical model id
- vercelAIGatewayCatalog/deepseek/deepseek-v3.2-thinking
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- DeepSeek
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 32 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Explore more models