Qwen3 Coder 480B A35B Instruct Turbo
Qwen coding model for software agents, repository edits, and code reasoning
Context
262,144
Max output
66,536
Input / 1M
$0.30
Output / 1M
$1.00
Providers
2
01Profile
Profile
Released
2025-07-23
Last updated
2026-06-11
Knowledge cutoff
2025-04
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
Yes
Structured output
Yes
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 2 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
7+ recent events since 2025-07-23
2026-06-10Price cutdeepinfraoutput / 1M$1.20→ $1.00
2026-06-10ContextveniceContext window256,000→ new
2026-06-10ContextveniceContext window—→ 256,000
2026-06-10ContextveniceMax output65,536→ new
2026-06-10ContextveniceMax output—→ 65,536
2026-02-26Addedveniceoffering→ new
2025-07-28Addeddeepinfraoffering→ new