DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & [technical report](h…
Model details →DeepSeek: R1 vs Qwen2.5 Coder 32B Instruct
DeepSeek: R1 wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reas…
Model details →Side-by-side comparison
| Capability | DeepSeek: R1 | Qwen2.5 Coder 32B Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 64K | 33K | 🏆 DeepSeek: R1 |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.70 | $0.66 | 🏆 Qwen2.5 Coder 32B Instruct |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $2.50 | $1.00 | 🏆 Qwen2.5 Coder 32B Instruct |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | — | 🏆 DeepSeek: R1 |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | — | 🏆 DeepSeek: R1 |
Frequently asked questions
Is DeepSeek: R1 better than Qwen2.5 Coder 32B Instruct?
DeepSeek: R1 wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between DeepSeek: R1 and Qwen2.5 Coder 32B Instruct?
Input: $0.70 vs $0.66 per 1M tokens. Output: $2.50 vs $1.00 per 1M tokens.
What context windows do DeepSeek: R1 and Qwen2.5 Coder 32B Instruct support?
DeepSeek: R1 supports up to 64K tokens. Qwen2.5 Coder 32B Instruct supports up to 33K tokens.
Do both DeepSeek: R1 and Qwen2.5 Coder 32B Instruct support tool calling?
DeepSeek: R1: yes. Qwen2.5 Coder 32B Instruct: not advertised.