Qwen3.8 Flash
Qwen vision-language model for visual reasoning, documents, and agent tasks
Context
1,048,576
Max output
131,072
Input / 1M
$0.11
Output / 1M
$0.38
Providers
22
01Profile
Profile
Released
2026-08-26
Last updated
2026-08-26
Knowledge cutoff
—
Weights
Closed
02Capabilities
Capabilities
Input
text · image · video
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
$0.02
Cache write
$0.20
03Pricing
Pricing across 19 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2026-08-26
2026-09-14Addeddeepinfraoffering→ new
2026-09-14Price cutvercelinput / 1M$0.16→ $0.15
2026-09-11Price cutofoxinput / 1M$0.15→ $0.11
2026-09-11Price cutofoxoutput / 1M$0.47→ $0.39
2026-09-10Price cutnano-gptinput / 1M$0.16→ $0.14
2026-09-10Price cutnano-gptoutput / 1M$0.47→ $0.42
2026-09-10Addedofoxoffering→ new
2026-09-08Added302aioffering→ new
2026-09-04Addedscnet-token-planoffering→ new
2026-09-03Price cutedenaiinput / 1M$0.16→ $0.15
2026-09-03Addednanoffering→ new
2026-09-02Addedrequestyoffering→ new