Qwen3 Coder 480B A35B

Provider: Alibaba (Qwen) CN

Input price
$0.30
/ 1M tokens
Output price
$1.00
/ 1M tokens
Cache price
$0.10
/ 1M tokens (read)
Context
262K tokens
Max output 66K tokens

Overview

Alibaba's Qwen3 Coder 480B A35B is a flagship Mixture-of-Experts coding model built for agentic workflows and long-context tool use.

Strengths

  • 262k token context window
  • Supports 65k max output
  • Native function calling and JSON mode
  • Cached input priced at $0.1 per million

Best use cases

  • Large-scale repository code generation
  • Complex multi-turn agentic tool calling
  • Automated debugging across massive files

Pricing position

Input is $0.3/M and output is $1/M, matching Codestral 2508 while undercutting Command A+'s $1.5/M output.

Caveats

No free tier available; smaller sibling Qwen3 Coder 30B provides a cheaper alternative at $0.07/M input.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
66K tokens
Knowledge cutoff
2025-06-30
Listed on OpenRouter
2025-07-23
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Function callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.08
1M (small app) 1 0.5 $0.80
10M (mid scale) 10 5 $8.00
100M (large) 100 50 $80.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen3-coder)