Deepseek R1 Distill Qwen 32B
Summary
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.
Classic open reasoning model for transparent math, coding, and deliberate problem solving
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | DeepSeek |
|---|---|
| Release date | 20 Jan 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | mit [Hugging Face] |
| Parameters | 684B [Hugging Face] |
| Context window | 80K (80,000 tokens) [models.dev] |
| Max output | 80K tokens [models.dev] |
| Knowledge cutoff | Jul 2024 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | No [models.dev] |
| Structured output | No [models.dev] |
| Hugging Face | deepseek-ai/DeepSeek-R1 [Hugging Face] |
Deepseek R1 Distill Qwen 32B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Cloudflare Workers AI @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | $0.50 | $4.88 | – | 80K | models.dev, 4 Oct 2026 |
| SiliconFlow deepseek-ai/DeepSeek-R1 | $0.50 | $2.18 | – | 164K | models.dev, 4 Oct 2026 |
| Hugging Face Inference Providers deepseek-ai/DeepSeek-R1 | $0.70 | $2.50 | – | 64K | models.dev, 4 Oct 2026 |
| OpenRouter deepseek/deepseek-r1 | $0.70 | $2.50 | – | 64K | OpenRouter, 4 Oct 2026 |
| Amazon Bedrock deepseek.r1-v1:0 | $1.35 | $5.40 | – | 128K | models.dev, 4 Oct 2026 |
| Amazon Bedrock us.deepseek.r1-v1:0 | $1.35 | $5.40 | – | 128K | models.dev, 4 Oct 2026 |
| Vercel AI Gateway deepseek/deepseek-r1 | $1.35 | $5.40 | – | 128K | models.dev, 4 Oct 2026 |
| Snowflake Cortex deepseek-r1 | – | – | – | 128K | models.dev, 4 Oct 2026 |
Frequently asked questions
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.
Change history
No changes detected since we started tracking this model. We re-check every source daily.
Sources
- https://openrouter.ai/deepseek/deepseek-r1
- https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b.toml
- https://huggingface.co/deepseek-ai/DeepSeek-R1
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/deepseek-ai/DeepSeek-R1.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/deepseek-ai/DeepSeek-R1.toml
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/deepseek.r1-v1:0.toml
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.deepseek.r1-v1:0.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/deepseek/deepseek-r1.toml
- https://github.com/sst/models.dev/blob/dev/providers/snowflake-cortex/models/deepseek-r1.toml