Qwen: QwQ 32B
Analysis Summary
QwQ 32B is a reasoning-focused open-weight model from Qwen (Alibaba) with a strong emphasis on mathematical and coding tasks. Its LiveCodeBench score of 0.631 is competitive with models costing far more, and it supports tool use and function calling, making it capable of structured agentic workflows.
For businesses, QwQ 32B is a strong fit for coding assistance, mathematical reasoning, and cost-sensitive automation pipelines. Its 131K context window is adequate for most tasks. Limitations include a relatively modest instruction-following score (IFBench 0.39) and no vision support, which restricts multimodal use cases.
At $0.15 input and $0.58 output per million tokens, it offers exceptional value for a model with this level of coding capability. Teams running high-volume coding or reasoning workloads on a budget should consider it seriously, though provider accessibility may be a consideration for some enterprise environments.
Assessed June 17, 2026
Editorial notes
QwQ 32B from Qwen delivers strong coding performance with a LiveCodeBench score of 0.631, tool use and function calling support, and very competitive pricing at $0.15 input per million tokens.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen: QwQ 32B compares
Qwen: QwQ 32B ranks #183 of 380 AI models we track for overall intelligence. Its 131K-token context window is larger than 59% of the models we list. At $0.15 per million input tokens it is cheaper than 57% of comparable models.
About Qwen: QwQ 32B
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,..
Capabilities
Architecture Detail
| Instruct Type | qwq |
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: QwQ 32B stack up?
Compare side-by-side with other efficient models.
Model Information
| OpenRouter ID |
qwen/qwq-32b
|
| Provider | qwen |
| Release Date | March 5, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 131,072 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.15 | $0.000150 |
| Output | $0.58 | $0.000580 |
Leaderboard Categories
External Resources
Frequently asked questions about Qwen: QwQ 32B
How much does Qwen: QwQ 32B cost?
Qwen: QwQ 32B costs $0.15 per million input tokens and $0.58 per million output tokens.
What is the context window of Qwen: QwQ 32B?
Qwen: QwQ 32B has a context window of 131,072 tokens (131K).
What can Qwen: QwQ 32B do?
Qwen: QwQ 32B supports tool use and function calling.
Who created Qwen: QwQ 32B?
Qwen: QwQ 32B is developed by Qwen and was released on March 5, 2025.
