v0-1.5-md

Name: v0-1.5-md
Author: v0

Multimodal reasoning model for visual analysis, planning, and tool use

Live

Open / InstallLast updated August 5, 2026

Description

Multimodal reasoning model for visual analysis, planning, and tool use. Supports a context window of 128,000 tokens. Supports extended reasoning. Supports tool calling. Input priced at $3 per million tokens. Weights are not publicly released; access is via the provider API.

Author

Platform

api

Pricing model

paid

Capabilities

Text generation
128,000 token context
Extended reasoning
Tool calling
File attachments
Image input

Benchmarks

No benchmark results have been added yet.