DeepSeek
DeepSeek V3.2
deepseek/deepseek-v3.2
Input
$0.28
per 1M tokens
Output
$0.42
per 1M tokens
Cached input
$0.028
per 1M tokens
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...
- Released
- Context window
- 164K tokens
- Max output
- 66K tokens
- Input
- text
- Output
- text
- Reasoning
- Yes
Price history
No price changes since we started tracking on .
Providers on OpenRouter
11 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| GMICloudfp8 | $0.209 | $0.31 | 164K | 100% | 100% |
| AtlasCloudfp8 | $0.26 | $0.38 | 164K | 100% | 99.86% |
| DeepInfrafp4 | $0.26 | $0.38 | 164K | 93.3% | 99.31% |
| Venice | $0.268 | $0.39 | 160K | 96.7% | 99.38% |
| Baidufp8 | $0.28 | $0.42 | 131K | — | 100% |
| SiliconFlowfp8 | $0.259 | $0.80 | 164K | 100% | 100% |
| DigitalOcean | $0.30 | $0.96 | 164K | 90.0% | 98.0% |
| Phala | $1.00 | $1.00 | 164K | 100% | 100% |
| $0.56 | $1.68 | 164K | 0.0% | 0.0% | |
| Mara | $3.00 | $4.50 | 33K | — | 100% |
| SambaNova | $3.00 | $4.50 | 33K | 88.9% | 82.4% |