May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) 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.…
Model details →DeepSeek: R1 0528 vs Qwen: Qwen3 VL 235B A22B Thinking
DeepSeek: R1 0528 and Qwen: Qwen3 VL 235B A22B Thinking are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust…
Model details →Side-by-side comparison
| Capability | DeepSeek: R1 0528 | Qwen: Qwen3 VL 235B A22B Thinking | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 164K | 131K | 🏆 DeepSeek: R1 0528 |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.45 | $0.26 | 🏆 Qwen: Qwen3 VL 235B A22B Thinking |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $2.15 | $2.60 | 🏆 DeepSeek: R1 0528 |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | Yes | 🏆 Qwen: Qwen3 VL 235B A22B Thinking |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is DeepSeek: R1 0528 better than Qwen: Qwen3 VL 235B A22B Thinking?
DeepSeek: R1 0528 and Qwen: Qwen3 VL 235B A22B Thinking are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
What's the price difference between DeepSeek: R1 0528 and Qwen: Qwen3 VL 235B A22B Thinking?
Input: $0.45 vs $0.26 per 1M tokens. Output: $2.15 vs $2.60 per 1M tokens.
What context windows do DeepSeek: R1 0528 and Qwen: Qwen3 VL 235B A22B Thinking support?
DeepSeek: R1 0528 supports up to 164K tokens. Qwen: Qwen3 VL 235B A22B Thinking supports up to 131K tokens.
Do both DeepSeek: R1 0528 and Qwen: Qwen3 VL 235B A22B Thinking support tool calling?
DeepSeek: R1 0528: yes. Qwen: Qwen3 VL 235B A22B Thinking: yes.