Image and video generation

Images and video from one API.

Generate images with FLUX.2 Pro or Imagen 4.0 and video with Veo 3.0 or Kling through one API, and pay for each output.

FLUX.2 Pro$0.0375 per megapixel

What you can build

Three jobs people run here. Each on a product you can start today.

Inference

FLUX.2 Pro for photoreal shots, Ideogram 3.0 for type in the image, Qwen Image Edit to change a picture with words.

Inference

Veo 3.0 Audio for scenes with sound, Kling v2.6 for motion, Seedance 2.0 Fast for quick drafts. Same key, same account.

Instance

Run ComfyUI or your own diffusion workflow on an RTX 4090 or L40S instance when you need custom nodes or weights.

Examples

Claude Code or Codex sends the request for you. Any OpenAI-compatible client works with one base URL.

Hand this to your agent

Add a Runcrate model to this project: run curl -fsSL"https://runcrate.ai/agents.md?intent=build"and follow it.

Your agent asks for an API key. Create a key

Works inClaude CodeCodexOpenCodeClineRoo CodeKilo CodeCursor

example

Models and tools

Name	Role	Runs on
FLUX.2 Pro	Photoreal text to image	Inference API
Imagen 4.0 Ultra	High-fidelity text to image	Inference API
Ideogram 3.0	Typography and graphic design	Inference API
Qwen Image Edit	Edit images with words	Inference API
Veo 3.0 Audio	Video scenes with sound	Inference API

How it works

01
Pick your model
FLUX, Imagen or Ideogram for images; Veo, Kling or Seedance for video. Each suits a different visual job.
02
Call the API
Send a prompt with the size or aspect ratio you want. Images come back as a URL; video jobs return a file when they finish.
03
Scale the pipeline
Batch thousands of generations into your product or creative workflow. You pay per output, and nothing while it is idle.

Pricing

Name

As billed