Image Generation API

Text + images → image. Generate images from a prompt, edit an image with an instruction, or combine several reference images. Each model has its own endpoint, POST /v1/images/{model}, with the options that model supports.

​

Models

32 models. Each name opens its API reference with every parameter.

​

How a request works

1. Send POST /v1/images/{model} with your prompt and options. The response returns a job id right away.
2. Poll GET /v1/images/{job_id} until status is succeeded. The response then holds the image URLs.

Async jobs covers job statuses and errors, and Media inputs covers passing reference images.

​

Useful options

• Several images per request
• Grounding and search grounding, for prompts about real, current things
• Transparent backgrounds

​

Pricing

Each model has its own price in credits, often by output size. GET /v1/models?type=image returns current prices, and POST /v1/cost quotes a request before you send it. You pay only for jobs that succeed; see Pricing & credits.