DeepSeek R1 Distill Qwen 32B represents a significant advancement in distilled large language models. Built upon the robust foundation of Qwen 2.5 32B and fine-tuned with outputs from DeepSeek R1, this model delivers exceptional performance. It has demonstrated superior capabilities compared to OpenAI's o1-mini across a range of benchmarks, setting new state-of-the-art records for dense models. Its competitive performance is further highlighted by impressive scores in AIME 2024 (72.6 pass@1), MATH-500 (94.3 pass@1), and a CodeForces Rating of 1691. This model is particularly well-suited for applications requiring high-quality text generation, complex code understanding, and advanced mathematical problem-solving. With a generous context window of 64K tokens and a maximum output of 4K tokens, it can handle extensive inputs and generate detailed responses. Pricing is highly competitive at $0.29 per 1M input tokens and $0.29 per 1M output tokens, making it an accessible and powerful tool for developers and researchers. Access this model for free on Multi AI.
✅ Best For
🚀 Capabilities
❌ Limitations
Specifications
| Provider | deepseek |
| Context Window | 32,768 tokens |
| Max Output | 32,768 tokens |
| Minimum Plan | Economy |
Pricing
| Input Price | $0.2900 / 1M tokens |
| Output Price | $0.2900 / 1M tokens |
💡 With PRO subscription, cost is reduced by 20%