Qwen3 30B A3B
Overview
Overview
Qwen3-30B-A3B is a smaller Mixture-of-Experts (MoE) model from the Qwen3 series by Alibaba, with 30.5 billion total parameters and 3.3 billion activated parameters. Features hybrid thinking/non-thinking modes, support for 119 languages, and enhanced agent capabilities. It aims to outperform previous models like QwQ-32B while using significantly fewer activated parameters.
Qwen3 30B A3B was released on April 29, 2025. API access is available through DeepInfra, Novita, Fireworks.
Performance
Timeline
Specifications
Benchmarks
Benchmarks
Qwen3 30B A3B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Jan 30 2026Pricing
Pricing
Pricing, performance, and capabilities for Qwen3 30B A3B across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.10 | $0.30 | 128.0K | 128.0K | 0.84 | 82.57 c/s | — | Text Image Audio Video | Text Image Audio Video |
 Novita | $0.10 | $0.44 | 128.0K | 128.0K | 0.73 | 88.84 c/s | — | Text Image Audio Video | Text Image Audio Video |
 Fireworks | $0.89 | $0.89 | 128.0K | 128.0K | 0.66 | 122.4 c/s | — | Text Image Audio Video | Text Image Audio Video |
Price Comparison for Qwen3 30B A3B
Price per 1M input tokens (USD), lower is better
llm-stats.com - Fri Jan 30 2026Throughput Comparison for Qwen3 30B A3B
Tokens per second, higher is better
llm-stats.com - Fri Jan 30 2026Latency Comparison for Qwen3 30B A3B
Time to first token (s), lower is better
llm-stats.com - Fri Jan 30 2026API Access
API Access Coming Soon
API access for Qwen3 30B A3B will be available soon through our gateway.
Recent Posts
Recent Reviews
FAQ
Common questions about Qwen3 30B A3B