Active
ByteDance: UI-TARS 7B
Multimodal model for analyzing text, images, documents, and rich media
Context
128,000
Max output
2,048
Input / 1M
$0.10
Output / 1M
$0.20
Providers
2
01Profile
Profile
Released
2025-07-22
Last updated
2025-07-22
Knowledge cutoff
—
Weights
Closed
02Capabilities
Capabilities
Input
image · text
Output
text
Reasoning
No
Tool calling
No
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 2 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
2+ recent events since 2025-07-22
2026-05-15Addedopenrouteroffering→ new
2026-03-15Addedkilooffering→ new