qwen/qwen3-coder-30b-a3b-instruct

Qwen3 Coder 30B A3B Instruct

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.

7/31/2025

160,000 tokens

Input: ¥16/M

Output: ¥79/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

Output

text

Supported Parameters

frequency_penalty

max_tokens

presence_penalty

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_p

Max Output Tokens

32,768

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "Qwen3-Coder-30B-A3B-Instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'