← model directory

cloudflare

qwen/qwq-32b

cloudflare/qwen/qwq-32b

↓ runs free on your own hardware

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

specs & pricing
Type
text
Provider
cloudflare
Model ID
cloudflare/qwen/qwq-32b
Context window
24K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.73 / 1M tokens
Output price
$1.10 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.