BlockRun
AI tools / Image Editing API

Edit an image with a prompt instead of a mask

Image-to-image editing through one endpoint: send a source image and a prompt, get the edit back. Priced per edit in USDC, quoted before the call runs.

The call

One endpoint, priced in dollars before it runs and settled in USDC. No API key and no account — the request pays for itself.

POST /api/v1/images/image2image
Host: blockrun.ai

Why per call

No seat, no minimum, no contract per vendor. Each request is quoted in dollars before it runs and settles on-chain, so an agent can pay for its own work without a human holding a credit card. How the payment works →

Questions

How is this different from generation?

Generation starts from a prompt alone; editing starts from an image you supply and changes it.

What does an edit cost?

The same per-image rate as generation on the model you pick, quoted before the request runs.

Do I need to supply a mask?

No. The prompt describes the change; no mask channel is required.

Which formats are accepted?

Standard web image formats, sent as a URL or inline data — the docs carry the exact request shape.