qwen/qwen3-coder-480b-a35b-instruct

Qwen/Qwen3-Coder-480B-A35B-Instruct

Context

128K

Input

text

Output

text

Tool calling

Supported

About this model

Qwen3-Coder-480B-A35B-Instruct is a massive 480B-parameter MoE model specialized in code generation and technical problem-solving. Featuring 35B active parameters per token through expert routing, it delivers state-of-the-art coding assistance with FP8 quantization for efficient deployment.

Compare Text Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Novita

Available

Input tokens

$0.290 / 1M tokens

Output tokens

$1.200 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Input tokens	$0.290 / 1M tokens
Output tokens	$1.200 / 1M tokens

Performance

Published evaluation results associated with this model.

Code Generation

HumanEval82.7

MBPP++78.9

MultiPL-E (Python)80.3

MultiPL-E (C++)76.4

Technical Problem Solving

LeetCode Hard71.5

CodeContests68.2

SWE-Bench Lite63.8

Code Understanding

RepoLevel Benchmark85.3

CodeXGLUE88.7

DS-100079.6

API example

Refer Documentation

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'