Qwen3-Omni Flash Realtime
Qwen omni model for text, vision, audio, and multimodal agent tasks
Context
65,536
Max output
16,384
Input / 1M
$0.23
Output / 1M
$0.92
Providers
2
01Profile
Profile
Released
2025-09-15
Last updated
2025-09-15
Knowledge cutoff
2024-04
Weights
Closed
02Capabilities
Capabilities
Input
text · image · audio · video
Output
text · audio
Reasoning
No
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
Not listed
Cache write
Not listed
03Pricing
Pricing across 2 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
2+ recent events since 2025-09-15
2025-10-14Addedalibabaoffering→ new
2025-10-14Addedalibaba-cnoffering→ new