AlibabaQwenTool use

Qwen3 Coder 480B A35B pricing

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used. This page tracks 2 listings in total. Highlighted lows are $0.220 per million input and $0.950 per million output (see table for which seller matches each).

262K context·2 providers·verified May 2, 2026
Best input$0.220per 1M tokens · Openrouter
Best output$0.950per 1M tokens · Openrouter

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 2 offers are listed for Qwen3 Coder 480B A35B. Best input in this view: Openrouter.

O
Openrouter
Input / 1M
$0.220
Output / 1M
$0.950
VA
Vercel Ai Gateway
Input / 1M
$0.400
Output / 1M
$1.60

Input vs output · per provider

Cost calculator

Use this block to stress test Qwen3 Coder 480B A35B cost without a spreadsheet. All estimates come from public list rates in this page.

Provider

In: $0.220/M·Out: $0.950/M

0.022000¢ / req

0.047500¢ / req

Daily
$6.95
Monthly
$209
Annual
$2.5K

Model specifications

These fields describe Qwen3 Coder 480B A35B as we store it (Family: Qwen. source: Alibaba). They sit next to price so buyers can check limits and tools in one place.

Context window
262,100 tokens
Max output
262,100 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Jul 2025
Primary provider
Alibaba
Model family
Qwen

Compare Qwen3 Coder 480B A35B

These links open full side by side pages for Qwen3 Coder 480B A35B. We picked pairs that people often shop together. 6 ready to open.

Frequently asked questions

Answers pull from the same numbers you see on this page. The short model note from our index: Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over ...

Yes. Qwen3 Coder 480B A35B is available on Openrouter, Vercel Ai Gateway.

Also from Alibaba

Other models by Alibaba with live pricing in our catalog.