DeepSeek
DeepSeek: R1 Distill Qwen 32B
DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.\n\nOther benchmark results include:\n\n- AIME 2024 pass@1: 72.6\n- MATH-500 pass@1: 94.3\n- CodeForces Rating: 1691\n\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.
| Specifications | |
|---|---|
| Provider | DeepSeek |
| Input pricing | $0.29/M tokens |
| Output pricing | $0.29/M tokens |
| Context length | 33K tokens |
| Max output | 33K tokens |
| Input modalities | text |
| Output modalities | text |
| Tokenizer | Qwen |
| Knowledge cutoff | 2024-07-31 |
| Content moderated | No |
| HuggingFace | deepseek-ai/DeepSeek-R1-Distill-Qwen-32B |
Supported Parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatstopstructured_outputstemperaturetop_logprobstop_p