deepseek/deepseek-v3.2
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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| StreamLake | $0.229 | $0.343 | 128K | 100% |
| Baidufp8 | $0.252 | $0.378 | 131K | 100% |
| SiliconFlowfp8 | $0.259 | $0.420 | 164K | 99.6% |
| DeepInfrafp4 | $0.260 | $0.380 | 164K | 99% |
| AtlasCloudfp8 | $0.260 | $0.380 | 164K | 99.9% |
| Novitafp8 | $0.269 | $0.400 | 164K | 100% |
| Alibaba | $0.370 | $1.11 | 131K | 98.8% |
| DigitalOcean | $0.425 | $1.36 | 128K | 99.8% |
| Friendli | $0.500 | $1.50 | 164K | 99.9% |
| $0.560 | $1.68 | 164K | 99.2% | |
| SambaNova | $3.00 | $4.50 | 33K | 98% |
DeepSeek V3.2 costs $0.229 per million input tokens and $0.343 per million output tokens via OpenRouter, making it 106th cheapest of 298 paid models.
DeepSeek V3.2 scores 41.7 on the Artificial Analysis Intelligence Index, ranking 38th of 180 benchmarked models, with a GPQA Diamond score of 84%.
DeepSeek V3.2 generates around 83 tokens per second with 688ms time-to-first-token (p50), the 91st fastest tracked model.
DeepSeek V3.2 supports a 131K-token context window and can output up to 64K tokens. It accepts text input.