R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving
https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run @cf/deepseek-ai/deepseek-r1-distill-qwen-32b deepseek-r1-distill-qwen-32b is listed for chat, reasoning workloads and supports a 32K context window.
Use it when Cloudflare Workers AI's free tier is enough for evaluation, demos, or light production traffic.
We only found this deepseek-r1-distill-qwen-32b listing on Cloudflare Workers AI in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | Free tier | 32K | Native | 10K neurons/day (shared) |
| Model | Provider | Context | Access |
|---|---|---|---|
| Mistral 7B | Cloudflare Workers AI | 33K | Free tier |
| Qwen 1.5 7B | Cloudflare Workers AI | 33K | Free tier |
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | Cloudflare Workers AI | 131K | Free tier |
| @cf/meta/llama-4-scout-17b-16e-instruct | Cloudflare Workers AI | 10.0M | Free tier |
| @cf/openai/gpt-oss-120b | Cloudflare Workers AI | 128K | Free tier |
deepseek-r1-distill-qwen-32b is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
deepseek-r1-distill-qwen-32b is tagged for reasoning in this catalog and works with OpenAI-compatible client libraries.
deepseek-r1-distill-qwen-32b is listed with free API access on Cloudflare Workers AI, subject to the provider's quota and account policy.
The model ID shown in this catalog is @cf/deepseek-ai/deepseek-r1-distill-qwen-32b.
The listed free tier limit is 10K neurons/day (shared). Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 32K tokens with up to 131K output tokens.
DeepSeek R1 Distill Qwen 32B is a distilled version of DeepSeek's reasoning model, fine-tuned from Qwen 32B to replicate R1's chain-of-thought reasoning behavior at a smaller, more efficient scale. Running on Cloudflare's edge network, it offers reasoning-model capabilities — step-by-step deliberation for math, logic, and coding problems — with the lower latency and cost profile of a 32B model. The 32K context window is adequate for focused reasoning tasks but limits its use for long-document analysis. Shares Cloudflare's 10,000 Neurons/day free pool and uses Cloudflare's native API format.
For API keys, setup steps, and provider-level limits, see the Cloudflare Workers AI provider page.