Qwen logo

Qwen3 Coder 30B A3B Instruct: Pricing, Context Window & Benchmarks

30B

by Qwen

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion. This model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats.

Input Price
$0.45/1M tokens
Output Price
$2.25/1M tokens
Intelligence
20.0
Coding
19.4

What you can do with Qwen3 Coder 30B A3B Instruct

Everyday Q&A and clear explanations

Writing help (emails, posts, summaries)

Idea generation and brainstorming

Learning support with step-by-step guidance

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Benchmark Highlights

6 tests
GPQA
51.6%
MMLU Pro
70.6%
LiveCodeBench
40.3%
Math 500
89.3%
AIME 2025
29.0%
HLE
4.0%
Metric Value
Provider Qwen
Context Window 160,000 tokens
Input Price $0.45/1M tokens
Output Price $2.25/1M tokens
Release Date Jul 31, 2025
Modalities text
Capabilities N/A

Compare Qwen3 Coder 30B A3B Instruct to other models

See how it stacks up on price, quality, and overall performance.

Frequently asked questions

What is Qwen3 Coder 30B A3B Instruct good for?

Use Qwen3 Coder 30B A3B Instruct for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Qwen3 Coder 30B A3B Instruct cost?

Pricing is based on usage. Current rates are $0.45/1M tokens for input and $2.25/1M tokens for output.

Can I try Qwen3 Coder 30B A3B Instruct for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Qwen3 Coder 30B A3B Instruct support images or audio?

Qwen3 Coder 30B A3B Instruct focuses on text-based tasks.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.