# Deepseek R1 Distill Qwen 32B

> Deepseek R1 Distill Qwen 32B is an open-weight language model from DeepSeek, released on 20 Jan 2025. It accepts text and generates text, with a 80K-token context window and up to 80K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.50 per million input tokens and $2.18 per million output tokens (SiliconFlow), across 7 providers we track.

Source page: https://www.aimodel.directory/models/deepseek-r1
Last verified: 4 Oct 2026

## Specifications

- **Developer:** DeepSeek
- **Release date:** 20 Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/deepseek-ai/DeepSeek-R1)
- **License:** mit (source: Hugging Face, https://huggingface.co/deepseek-ai/DeepSeek-R1)
- **Parameters:** 684B (source: Hugging Face, https://huggingface.co/deepseek-ai/DeepSeek-R1)
- **Context window:** 80K (80,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Max output:** 80K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Knowledge cutoff:** Jul 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml)
- **Hugging Face:** deepseek-ai/DeepSeek-R1 (source: Hugging Face, https://huggingface.co/deepseek-ai/DeepSeek-R1)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Cloudflare Workers AI | $0.50 | $4.88 | – | 80K |
| SiliconFlow | $0.50 | $2.18 | – | 164K |
| Hugging Face Inference Providers | $0.70 | $2.50 | – | 64K |
| OpenRouter | $0.70 | $2.50 | – | 64K |
| Amazon Bedrock | $1.35 | $5.40 | – | 128K |
| Amazon Bedrock | $1.35 | $5.40 | – | 128K |
| Vercel AI Gateway | $1.35 | $5.40 | – | 128K |
| Snowflake Cortex | – | – | – | 128K |

## FAQ

### What is the context window of Deepseek R1 Distill Qwen 32B?

Deepseek R1 Distill Qwen 32B has a context window of 80,000 tokens (80K) and can generate up to 80,000 tokens in a single response, according to models.dev.

### How much does the Deepseek R1 Distill Qwen 32B API cost?

Deepseek R1 Distill Qwen 32B is listed from $0.50 per million input tokens and $2.18 per million output tokens (SiliconFlow). Prices last verified 4 Oct 2026.

### Is Deepseek R1 Distill Qwen 32B open source?

Deepseek R1 Distill Qwen 32B is an open-weight model: its weights are published on Hugging Face as deepseek-ai/DeepSeek-R1 under the mit license. Check the license terms before commercial use.

### When was Deepseek R1 Distill Qwen 32B released?

DeepSeek released Deepseek R1 Distill Qwen 32B on 20 Jan 2025, according to models.dev.

### Which providers offer Deepseek R1 Distill Qwen 32B?

We track Deepseek R1 Distill Qwen 32B on 7 providers: Cloudflare Workers AI, SiliconFlow, Hugging Face Inference Providers, OpenRouter, Amazon Bedrock, Vercel AI Gateway, Snowflake Cortex.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Deepseek R1 Distill Qwen 32B", https://www.aimodel.directory/models/deepseek-r1