Models

Choose the right
model for the agent job.

AnyCap exposes multimodal models through one capability runtime and one CLI. This page helps teams choose the right model for a given agent workflow instead of treating every image or video request the same way.

Early Access

AnyCap is currently in early access. Capabilities shown on this page are available to early access users. Request access on GitHub to get started.

Image generation

Seedream 5

A strong default for polished first-pass image generation tasks.

Nano Banana Pro

A better fit for revision loops and prompt-based image editing.

Video generation

Veo 3.1

The current video generation model for text-to-video workflows through AnyCap.

Any Capability Context Guide

Choose the rightmodel for the agent job.

Image generation

Seedream 5

Nano Banana Pro

Video generation

Veo 3.1

Choose the rightmodel for the agent job.

Image generation

Seedream 5

Nano Banana Pro

Video generation

Veo 3.1

Choose the right
model for the agent job.

Choose the right
model for the agent job.