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 bench…
Model details →DeepSeek: R1 Distill Qwen 32B vs Mistral: Mistral Small 4
Mistral: Mistral Small 4 wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from Magistral, multimodal understanding from Pixtral, an…
Model details →Side-by-side comparison
| Capability | DeepSeek: R1 Distill Qwen 32B | Mistral: Mistral Small 4 | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 33K | 262K | 🏆 Mistral: Mistral Small 4 |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.29 | $0.15 | 🏆 Mistral: Mistral Small 4 |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.29 | $0.60 | 🏆 DeepSeek: R1 Distill Qwen 32B |
| Tool / function calling First-class support for emitting structured tool calls. | — | Yes | 🏆 Mistral: Mistral Small 4 |
| Vision input Accepts image inputs alongside text. | — | Yes | 🏆 Mistral: Mistral Small 4 |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is DeepSeek: R1 Distill Qwen 32B better than Mistral: Mistral Small 4?
Mistral: Mistral Small 4 wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between DeepSeek: R1 Distill Qwen 32B and Mistral: Mistral Small 4?
Input: $0.29 vs $0.15 per 1M tokens. Output: $0.29 vs $0.60 per 1M tokens.
What context windows do DeepSeek: R1 Distill Qwen 32B and Mistral: Mistral Small 4 support?
DeepSeek: R1 Distill Qwen 32B supports up to 33K tokens. Mistral: Mistral Small 4 supports up to 262K tokens.
Do both DeepSeek: R1 Distill Qwen 32B and Mistral: Mistral Small 4 support tool calling?
DeepSeek: R1 Distill Qwen 32B: not advertised. Mistral: Mistral Small 4: yes.