Qwen: Qwen3 30B A3B
Analysis Summary
Qwen3 30B A3B is a mixture-of-experts model from Alibaba that activates only 3B parameters per forward pass, enabling fast and cheap inference. It supports tool use and function calling across a 128K context window, with a strong math index of 72.3 relative to its intelligence index of 9.3. LiveCodeBench at 0.506 is competitive for the price.
For businesses, it suits mathematical automation, structured data tasks, and lightweight tool-calling pipelines where speed and cost efficiency matter. Its agentic index of 14.1 is low, limiting reliability in complex multi-step workflows. Vision is not supported.
At $0.12/1M input and $0.50/1M output, it is priced competitively for a model with this math capability. Teams running quantitative or structured tasks at volume will find it a useful option, though for general reasoning or coding quality the Qwen3 32B offers a better overall profile.
Assessed June 17, 2026
Editorial notes
Qwen3 30B A3B is a compact MoE model from Alibaba with tool use, strong math scores, and a 128K context at $0.12/1M input, offering reasonable value for structured and mathematical workloads.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen: Qwen3 30B A3B compares
Qwen: Qwen3 30B A3B ranks #232 of 380 AI models we track for overall intelligence, #227 of 317 for coding, #230 of 292 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $0.12 per million input tokens it is cheaper than 60% of comparable models.
About Qwen: Qwen3 30B A3B
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique..
Capabilities
Architecture Detail
| Instruct Type | qwen3 |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3 30B A3B stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen3-30b-a3b
|
| Provider | qwen |
| Release Date | April 28, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.12 | $0.000120 |
| Output | $0.50 | $0.000500 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Qwen: Qwen3 30B A3B
How much does Qwen: Qwen3 30B A3B cost?
Qwen: Qwen3 30B A3B costs $0.12 per million input tokens and $0.50 per million output tokens.
What is the context window of Qwen: Qwen3 30B A3B?
Qwen: Qwen3 30B A3B has a context window of 131,072 tokens (131K).
Is Qwen: Qwen3 30B A3B good for coding?
On our coding benchmark index, Qwen: Qwen3 30B A3B ranks #227 of 317 models, placing it in the broader range of the field for code generation and debugging.
What can Qwen: Qwen3 30B A3B do?
Qwen: Qwen3 30B A3B supports tool use and function calling.
Who created Qwen: Qwen3 30B A3B?
Qwen: Qwen3 30B A3B is developed by Qwen and was released on April 28, 2025.
