Compare two models
Select any two models. Input, output, cached, and context rarely move together — the cheaper model on one line isn't always the cheaper one on the next.
Description
Qwen3 Coder 480B A35B is a 480-billion-parameter mixture-of-experts code-focused language model from Alibaba that activates 35 billion parameters per token.
OpenAI's frontier model for complex professional workloads. 1M token context, text + image input, native computer use.
I/O price /1M
$0.3/$1.00
$5.00/$30.00
Input /1M
$0.3
$5.00
Output /1M
$1.00
$30.00
Cached in /1M
$0.1
$0.5
Context
262K
1M
Δ input since launch
increased 36.4%
—
Δ output since launch
decreased 44.4%
—
Released
Jul 2025
Apr 2026
Status
—
—
Provider
Alibaba
OpenAI