Integrate multimodal vision capabilities using ByteDance: UI-TARS 7B , designed to process both text and images seamlessly. This model delivers cost-effective pricing at $0.10/1M input and $0.20/1M output tokens. Access ByteDance: UI-TARS 7B via the Kilo Gateway API with up to 2K output tokens.
Tokens
Tokens
Tokens
ByteDance: UI-TARS 7B by Kilo Gateway costs $0.10 per 1M input tokens and $0.20 per 1M output tokens.