Qwen3 30B A3B: Benchmarks, Pricing & Context Window
Qwen3 30B A3B is a language model from Qwen, released in April 2025, with a 128K-token context window, and pricing from $0.100/M input and $0.440/M output.
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,
Qwen3 30B A3B benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Qwen3 30B A3B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Qwen3 30B A3B holds up as conversations get longer.
Quality Tracker
Qwen3 30B A3B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Oct 02 2026Qwen3 30B A3B pricing
Providers
Qwen3 30B A3B starts at $0.100 per million input tokens and $0.300 per million output tokens via DeepInfra. See all 3 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.100 | — | $0.300 | 128.0K/128.0K | 0.84 | — | / |
 Novita | $0.100 | — | $0.440 | 128.0K/128.0K | 0.73 | — | / |
 Fireworks | $0.890 | — | $0.890 | 128.0K/128.0K | 0.66 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Qwen3 30B A3B model size
Qwen3 30B A3B has 30.5 billion parameters and was trained on 36 trillion tokens. See how it compares to other models in the same parameter range.
Qwen3 30B A3B context window
Input and output token limits for Qwen3 30B A3B, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Qwen3 30B A3B.
Qwen3 30B A3B latency
Qwen3 30B A3B time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Qwen3 30B A3B examples
Recent arena outputs from Qwen3 30B A3B, picked from the highest-ranked matchups.
Qwen3 30B A3B license
Qwen3 30B A3B is released under the Apache 2.0 license, which permits commercial use, has 30.5B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 30.5B
Apache License 2.0 - allows commercial use
Qwen3 30B A3B resources
Official sources for Qwen3 30B A3B: provider documentation, official playground, source repository, model weights.
Qwen3 30B A3B vs other models
The most-compared alternatives to Qwen3 30B A3B are Qwen3 14B, DeepSeek R1 Distill Llama 70B, Phi 4 Reasoning. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Qwen3 30B A3B
Models ranked just above and below Qwen3 30B A3B by LLM Stats score.
FAQ
Common questions about Qwen3 30B A3B.