Qwen: Qwen3 235B A22B Instruct 2507
Analysis Summary
Qwen3 235B A22B Instruct 2507 is a large mixture-of-experts model from Alibaba's Qwen3 family, released in July 2025, with 235B total parameters and 22B active. Its intelligence index of 25.0 and coding index of 22.1 are strong, and its math index of 71.7 and AIME score of 0.717 confirm excellent quantitative reasoning. LiveCodeBench at 0.524 and TerminalBench at 0.152 indicate real coding and agentic capability. Tool use and function calling are supported, with a 262K context window.
For businesses, it is a compelling choice for coding assistance, mathematical analysis, and structured automation at a price point that is hard to match. The MoE architecture delivers frontier-adjacent capability at a fraction of the cost of dense models. No vision support is a limitation for multimodal workflows, and the agentic index of 24.2 is functional but not leading-class.
At $0.09 input and $0.10 output per million tokens, it offers exceptional value for technical workloads. The -4 point regional penalty applies for provider accessibility. Teams prioritising cost-efficient coding and reasoning at scale will find it one of the strongest value propositions in its tier.
Assessed June 9, 2026
Editorial notes
Qwen3 235B A22B Instruct 2507 is a large MoE model with strong coding and math benchmarks, tool use, and exceptionally low pricing for its capability level.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen: Qwen3 235B A22B Instruct 2507 compares
Qwen: Qwen3 235B A22B Instruct 2507 ranks #150 of 380 AI models we track for overall intelligence, #135 of 317 for coding, #164 of 292 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $0.09 per million input tokens it is cheaper than 68% of comparable models.
About Qwen: Qwen3 235B A22B Instruct 2507
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3 235B A22B Instruct 2507 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen3-235b-a22b-2507
|
| Provider | qwen |
| Release Date | July 21, 2025 |
| Context Length | 262,144 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.09 | $0.000090 |
| Output | $0.10 | $0.000100 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Qwen: Qwen3 235B A22B Instruct 2507
How much does Qwen: Qwen3 235B A22B Instruct 2507 cost?
Qwen: Qwen3 235B A22B Instruct 2507 costs $0.09 per million input tokens and $0.10 per million output tokens.
What is the context window of Qwen: Qwen3 235B A22B Instruct 2507?
Qwen: Qwen3 235B A22B Instruct 2507 has a context window of 262,144 tokens (262K).
Is Qwen: Qwen3 235B A22B Instruct 2507 good for coding?
On our coding benchmark index, Qwen: Qwen3 235B A22B Instruct 2507 ranks #135 of 317 models, placing it in the broader range of the field for code generation and debugging.
What can Qwen: Qwen3 235B A22B Instruct 2507 do?
Qwen: Qwen3 235B A22B Instruct 2507 supports tool use and function calling.
Who created Qwen: Qwen3 235B A22B Instruct 2507?
Qwen: Qwen3 235B A22B Instruct 2507 is developed by Qwen and was released on July 21, 2025.
