All Models

Qwq 32b

Reasoning Tool Calling Open Weights

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.

Providers 5
Released Nov 28, 2024
Input Modalities text
Output Modalities text
Tarsk Use coding

Available Providers (5)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Nvidia qwen/qwq-32b $0.00/MTok $0.00/MTok 128K 4.1K
Alibaba (China) qwq-32b $0.29/MTok $0.86/MTok 131.1K 8.2K
Abacus Qwen/QwQ-32B $0.40/MTok $0.40/MTok 32.8K 32.8K
Cloudflare AI Gateway workers-ai/@cf/qwen/qwq-32b $0.66/MTok $1.00/MTok 128K 16.4K
Cloudflare Workers AI @cf/qwen/qwq-32b $0.66/MTok $1.00/MTok 128K 16.4K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output