This model is not part of the weekly automatic sync. The figures below were confirmed on 2026-08-13.
Qwen 2.5 32B based R1 inferential distillation model. Optimized RTX 4090/A100 single GPU hosting
DeepSeek R1 Distill Qwen 32B — DeepSeek. Context window 128,000 tokens. API pricing (per 1M tokens): Input $0.3, Output $0.6. License: Open-Weight. GPQA Diamond 64.1%.
| Provider | DeepSeek |
|---|---|
| Tier | Small |
| Context window | 128,000 tokens |
| Max output | 8,192 tokens |
| License | Open-Weight |
| API pricing (per 1M tokens) · Input | $0.3 |
| API pricing (per 1M tokens) · Output | $0.6 |
| GPQA Diamond | 64.1% |
LMArena (CC-BY 4.0, best reasoning setting) · GPQA Diamond: Epoch AI (CC-BY 4.0)
Compare in the full catalog