Qwen3.8 2.4T A95B
Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows
Context
1,048,576
Max output
1,010,000
Input / 1M
$2.00
Output / 1M
$6.00
Providers
12
01Profile
Profile
Released
2026-08-12
Last updated
2026-08-26
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 13 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2026-08-12
2026-09-14Removednano-gptofferingremoved→ new
2026-09-09ContextkiloMax output262,144→ new
2026-09-09ContextopenrouterMax output262,144→ new
2026-09-03ContextkiloContext window—→ 1,000,000
2026-09-03ContextkiloMax output—→ 262,144
2026-09-03ContextopenrouterMax output—→ 262,144
2026-09-02Addedrequestyoffering→ new
2026-09-01ContextkiloContext window1,000,000→ new
2026-09-01ContextkiloMax output262,144→ new
2026-09-01ContextopenrouterMax output262,144→ new
2026-08-31Addedaihubmixoffering→ new
2026-08-31ContextkiloContext window1,000,000→ new