Should you use qwq-32b?
qwq-32b is listed for chat workloads and supports a 8K context window.
Use it when Cloudflare Workers AI's free tier is enough for evaluation, demos, or light production traffic.
https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run @cf/qwen/qwq-32b qwq-32b is listed for chat workloads and supports a 8K context window.
Use it when Cloudflare Workers AI's free tier is enough for evaluation, demos, or light production traffic.
We only found this qwq-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/qwen/qwq-32b | Free tier | 8K | Native | Varies |
| Model | Provider | Context | Access |
|---|---|---|---|
| Mistral 7B | Cloudflare Workers AI | 33K | Check provider |
| Qwen 1.5 7B | Cloudflare Workers AI | 33K | Check provider |
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | Cloudflare Workers AI | 24K | Free tier |
| @cf/meta/llama-4-scout-17b-16e-instruct | Cloudflare Workers AI | 131K | Free tier |
| @cf/openai/gpt-oss-120b | Cloudflare Workers AI | 128K | Free tier |
qwq-32b is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
qwq-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/qwen/qwq-32b.
qwq-32b is scheduled for retirement on 2026-11-20. After that date, requests will return HTTP 410 Gone (Error 5028). The recommended official alternative is Qwen 3.8 27B.
The listed context window is 8K tokens with up to 4K output tokens.
QWQ-32B is Qwen's reasoning-focused model, running on Cloudflare Workers AI at the edge. With chain-of-thought deliberation capability at a 32B scale, it targets math, logic, and multi-step problem-solving tasks where explicit reasoning produces better results than single-pass generation. The 32K context window is narrower than general-purpose models but sufficient for most reasoning tasks. Like all Cloudflare Workers AI models, it draws from the shared 10,000 Neurons/day free pool and uses Cloudflare's native API. A good option for developers who want to test reasoning-model behavior without the overhead of larger alternatives like DeepSeek-R1.
For API keys, setup steps, and provider-level limits, see the Cloudflare Workers AI provider page.