DeepSeek V3.2
ModelOpen sourceActiveby DeepSeek · family “deepseek-v”
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... (description from the OpenRouter listing)
in: textout: textReasoningTool useStructured output
Epoch Capabilities Index
146.3 #70 of 268
90% CI 144.0 – 147.4
Released
1 Dec 2025
Context window
164K tokens
Max output
66K tokens
Input $ / 1M tokens
$0.28
Output $ / 1M tokens
$0.42
Cached input $ / 1M
$0.028
Each benchmark shown separately with its own source
Benchmark results (6)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| LMCA | agents | 15.2% | 22% | — | — | External ↗ |
| DTBench | reasoning | 62.7% | 63% | — | — | External ↗ |
| Chess Puzzles | games | 14.0% ±3.5 | 19% | — | 16 Dec 2025 | Eval log ↗ |
| Aider polyglot | coding | 74.2% | 84% | — | — | External ↗ |
| OTIS Mock AIME 2024-2025 | math | 87.8% ±4.1 | 88% | — | 16 Dec 2025 | Eval log ↗ |
| GPQA diamond | science | 83.4% ±2.0 | 87% | — | 16 Dec 2025 | Eval log ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
12 recorded prices on 6 Dec 2025 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 8h ago. Steps show when the price changed.
Events
- Price rise+4%DeepSeek V3.2 API price raisedOpenRouter models API
- RetirementDeepSeek V3.2 scheduled for retirementOpenRouter models API
- Open releaseMajorDeepSeek releases DeepSeek V3.2Epoch AI Benchmarking Hub