R1 Distill Qwen 32B
Provider: DeepSeek CN
Overview
DeepSeek R1 Distill Qwen 32B is a cost-optimized reasoning model from DeepSeek targeting complex structured generation and extensive context processing. It offers a substantial 128,000 token context window and a significant 32,768 token maximum output length.
Strengths
- Features a large 128,000 token context window for extensive input processing.
- Provides a substantial maximum output of 32,768 tokens for detailed responses.
- Offers a competitive, balanced $0.29/M token pricing for both input and output.
- Supports JSON mode for reliable structured data generation.
- Includes 'thinking' capability for enhanced problem-solving and reasoning.
Best use cases
- Processing and summarizing large legal documents or technical manuals.
- Generating comprehensive structured data responses in JSON format.
- Developing complex AI agents requiring iterative reasoning and thought processes.
- Long-form content creation that leverages extensive background information.
- Analyzing and debugging large codebases requiring broad contextual understanding.
Pricing position
At $0.29/M for both input and output, this model is positioned competitively within DeepSeek's portfolio. Its output price is significantly lower than DeepSeek V3.2 ($0.378/M) and much cheaper than V3.1 ($0.79/M). It also offers a more affordable output price than many similarly-priced peers like MiniMax M2.1 ($0.95/M) or Gemini 2.5 Flash ($2.5/M).
Caveats
The R1 Distill Qwen 32B does not offer a free tier for initial exploration or low-volume usage. While possessing a large context, it is not as extensive as DeepSeek V4 Flash's 1M token window. Users needing different pricing profiles, or those seeking models with explicitly stated multimodal capabilities, may consider other options.
Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.
Key facts
- Max output
- 33K tokens
- Tracked since
- 2026-05-08
- Last updated
- 2026-06-16
Features
Price history
- 2026-06-16 No longer listed
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.04 |
| 1M (small app) | 1 | 0.5 | $0.43 |
| 10M (mid scale) | 10 | 5 | $4.35 |
| 100M (large) | 100 | 50 | $43.50 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from DeepSeek
Similar-priced models
Source: OpenRouter API