Qwen3 Coder API

Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
Alibaba's 480B-parameter coding model — 262K-token context (extendable to 1M), built for agentic coding.
Context
262K tokens
Input
$2.6 / 1M tokens
Output
$2.6 / 1M tokens
Released
Sep 9, 2025

How to use Qwen3 Coder API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Qwen3 Coder API Pricing

TypePrice
Input
$2.6 / 1M tokens
Output
$2.6 / 1M tokens

The only documented caveat found for this exact model is that pricing varies by provider, with one listing noting Alibaba’s API rates may differ from other providers.

Qwen3 Coder Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Intelligence
11.9
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 22, 2026
Math
39.3
Composite score across standardised mathematics evaluations, measured independently by Artificial AnalysisSourceSeptember 22, 2026

Qwen3 Coder vs other models

ModelInputOutputContextBest for
Qwen3 Coder
This page
$2.6 / 1M tokens
$2.6 / 1M tokens
262K tokens
Agentic workflows and structured output
$1.95 / 1M tokens
$9.75 / 1M tokens
262K tokens
Coding + agents
$0.61893 / 1M tokens
$4.40128 / 1M tokens
256K tokens
Multimodal + agents
$0.65 / 1M tokens
$3.9 / 1M tokens
262K tokens
Coding + agents

Frequently asked questions

Qwen3 Coder has a 262,000 tokens context window and can return up to 65,536 tokens.

Qwen3 Coder takes text as input and returns text.

Use Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Qwen3 Coder became available on September 9, 2025.

Qwen3 Coder is priced at input $2.6 / 1M tokens, output $2.6 / 1M tokens.

Yes, Qwen3 Coder can stream responses as they are generated.

Qwen3 Coder was built by Alibaba Cloud.

Qwen3 Coder is a chat model built by Alibaba Cloud, described as a coding agent for text-to-text tasks.

Yes, it supports parallel tool calls, structured output, and tool use, and is described by Alibaba as a coding agent.

It supports parallel tool calls, tool use, and structured output alongside streaming responses.

Start building with Qwen3 Coder

Get API Key
1000+ models, one API.