Qwen3.6 Max Preview
Flagship Qwen model for complex reasoning, coding, and agentic workflows
Context
262,144
Max output
65,536
Input / 1M
$1.03
Output / 1M
$6.16
Providers
12
01Profile
Profile
Released
2026-04-20
Last updated
2026-05-09
Knowledge cutoff
2025-04
Weights
Closed
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
$0.13
Cache write
$1.63
03Pricing
Pricing across 13 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2026-04-20
2026-09-10Addedofoxoffering→ new
2026-08-20Addedllmgateway-providersoffering→ new
2026-08-19Price upofoxinput / 1M$2.00→ $2.15
2026-08-19Price upofoxoutput / 1M$12.00→ $12.86
2026-08-19ContextpioneerContext window—→ 240,000
2026-08-19ContextpioneerMax output—→ 64,000
2026-08-06Addedofoxoffering→ new
2026-08-03Price cutnano-gptinput / 1M$1.30→ $1.04
2026-08-03Price cutnano-gptoutput / 1M$7.80→ $6.24
2026-08-03Contextnano-gptContext window245,800→ 245,760
2026-08-03Contextnano-gptMax output65,536→ new
2026-08-02Price cutkiloinput / 1M$1.04→ $1.03