Qwen3 Coder 30B A3B Instructon Krater.ai

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.

Released July 31, 2025

Specifications

Qwen3 Coder 30B A3B Instruct at a glance

Context

262.1K tokens

Max output

32.8K tokens

Input

Text

Output

Text

Input price

$0.07 / 1M

Output price

$0.27 / 1M

Knowledge cutoff

2025-06-30

Tool callingStructured outputs

Capabilities

What it is good at

Catalog capabilities

  • Generates text responses
  • Supports tool calling
  • Supports structured outputs

Good for

Long documentsUse with toolsStructured responses

Benchmarks

Catalog data, not Krater benchmarks.

Design Arena uicomponent rank

#84

Design Arena dataviz rank

#85

FAQ

Questions about Qwen3 Coder 30B A3B Instruct

Clear answers based on the model catalog and Krater access.

Qwen3 Coder 30B A3B Instruct supports a context window of 262,144 tokens.

Use Qwen3 Coder 30B A3B Instruct in your API

Connect with Krater's unified API.

API access

Ready to use Qwen3 Coder 30B A3B Instruct?

Access leading models in one focused workspace.