Qwen3.5 Flash
Qwen vision-language model for visual reasoning, documents, and agent tasks
Context
1,020,000
Max output
1,020,000
Input / 1M
$0.03
Output / 1M
$0.29
Providers
8
01Profile
Profile
Released
2026-02-23
Last updated
2026-03-20
Knowledge cutoff
2025-04
Weights
Closed
02Capabilities
Capabilities
Input
text · image · video
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 10 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2026-02-23
2026-09-10Addedofoxoffering→ new
2026-08-27Addedorcarouteroffering→ new
2026-08-09Addedmerge-gatewayoffering→ new
2026-08-07Addedempiriolabsoffering→ new
2026-08-07Contextnano-gptMax output65,536→ new
2026-08-07Contextnano-gptMax output65,536→ new
2026-08-07ContextvercelContext window1,000,000→ new
2026-08-06Addedofoxoffering→ new
2026-08-03Price upnano-gptinput / 1M$0.09→ $0.10
2026-08-03Price upnano-gptoutput / 1M$0.36→ $0.40
2026-08-03Price upnano-gptinput / 1M$0.09→ $0.10
2026-08-03Price upnano-gptoutput / 1M$0.36→ $0.40