Qwen3.6 35B Fast
Efficient model for low-latency assistance, extraction, and routine automation
Context
131,056
Max output
131,056
Input / 1M
$0.29
Output / 1M
$1.15
Providers
1
01Profile
Profile
Released
2026-04-01
Last updated
2026-04-01
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
No
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
5+ recent events since 2026-04-01
2026-05-22Price upneuralwattinput / 1M$0.05→ $0.29
2026-05-22Price upneuralwattoutput / 1M$0.10→ $1.15
2026-05-16ContextneuralwattContext window131,072→ 131,056
2026-05-16ContextneuralwattMax output131,072→ 131,056
2026-04-27Addedneuralwattoffering→ new