Qwen: Qwen3 30B A3B Instruct 2507
Analysis Summary
Qwen3 30B A3B Instruct 2507 is a compact mixture-of-experts model from Alibaba's Qwen team, updated July 2025 with a 131K context window and support for tool use and function calling. Its math index of 66.3 and livecodebench score of 0.515 are strong for a model at this price point, and MMLU Pro (0.777) and GPQA (0.659) suggest reasonable general knowledge breadth.
For businesses, this model is well suited to structured content generation, SEO workflows, and coding assistance where cost efficiency matters. The agentic index of 8.1 is low, limiting its usefulness for autonomous multi-step pipelines. Instruction following (0.331 ifbench) is adequate but not best-in-class.
At $0.048 input / $0.193 output per million tokens, this is one of the most cost-effective options in the batch for teams needing a capable general-purpose model on a tight budget. The provider's adoption profile should be considered when evaluating enterprise fit.
Assessed June 6, 2026
Editorial notes
Qwen3 30B A3B Instruct 2507 offers strong math and coding benchmarks for its size with tool use, function calling, and very competitive pricing, though its agentic score is limited.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen: Qwen3 30B A3B Instruct 2507 compares
Qwen: Qwen3 30B A3B Instruct 2507 ranks #235 of 378 AI models we track for overall intelligence, #191 of 315 for coding, #268 of 289 for agentic tasks. Its 131K-token context window is larger than 60% of the models we list. At $0.05 per million input tokens it is cheaper than 73% of comparable models.
About Qwen: Qwen3 30B A3B Instruct 2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3 30B A3B Instruct 2507 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen3-30b-a3b-instruct-2507
|
| Provider | qwen |
| Release Date | July 29, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 32,000 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.05 | $0.000048 |
| Output | $0.19 | $0.000193 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Qwen: Qwen3 30B A3B Instruct 2507
How much does Qwen: Qwen3 30B A3B Instruct 2507 cost?
Qwen: Qwen3 30B A3B Instruct 2507 costs $0.05 per million input tokens and $0.19 per million output tokens.
What is the context window of Qwen: Qwen3 30B A3B Instruct 2507?
Qwen: Qwen3 30B A3B Instruct 2507 has a context window of 131,072 tokens (131K).
Is Qwen: Qwen3 30B A3B Instruct 2507 good for coding?
On our coding benchmark index, Qwen: Qwen3 30B A3B Instruct 2507 ranks #191 of 315 models, placing it in the broader range of the field for code generation and debugging.
What can Qwen: Qwen3 30B A3B Instruct 2507 do?
Qwen: Qwen3 30B A3B Instruct 2507 supports tool use and function calling.
Who created Qwen: Qwen3 30B A3B Instruct 2507?
Qwen: Qwen3 30B A3B Instruct 2507 is developed by Qwen and was released on July 29, 2025.
