DeepSeek V3.2
Specifications
- Input
- Output
- Context window
- 164K tokens
- Released
- Dec 2025
Performance
- Speed
- 16 t/s
- TTFT
- 1.6s
- Latency
- —
- Intelligence
- —
Pricing
- Input
- €0.35 per 1M tokens
- Output
- €0.58 per 1M tokens
About this model
DeepSeek V3.2 is the latest iteration of the DeepSeek V3 series with significant performance improvements. Features enhanced reasoning, coding capabilities, and better instruction following across diverse tasks.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- Hybrid Default on
Knowledge horizon
Knowledge cutoff Dec 2025
Released Dec 2025
Today
Training to release 0 mo Since release 5 mo
See also
Add Model to Comparison
Search for a model to add