# QwQ 32B: AI model fact sheet

- **Provider:** qwen
- **Released:** 2025-03-05
- **Context window:** 40,000 tokens
- **Parameters:** 32B
- **API pricing:** $0.50 / 1M input, $1.50 / 1M output
- **OpenRouter ID:** qwen/qwq-32b
- **Capabilities:** conversation, reasoning, code-generation, analysis

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.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| Throughput | 430.1 tokens/s |
| Latency | 4.54s |
| LiveCodeBench | 63.4% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/qwq-32b