DeepSeek v3.2
About this model
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)
Performance Tier
DeepSeek v3.2 is a flagship model from DeepSeek : the most capable in their lineup.
Best-in-class model from this provider. Highest performance across benchmarks, ideal for demanding tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.260 |
| Output (completion) | $0.380 |
| Cache read | $0.130 |
Capabilities
Benchmarks
Recommended Use Cases
Strengths
- Excellent price-to-performance ratio
- Top-tier math reasoning for an open model (AIME 93.1%)
- Open-weight model (transparency and self-hosting)
- Strong coding with Sparse Attention for efficient inference
Limitations
- May lag behind top proprietary models on creative tasks
- Less extensive safety tuning than Claude/GPT
Resources
This model may use your data for training
