p-image-Edit API

What is p-image-Edit?

Use the public identifier di-prunaaip-image-edit-75a811a0a4 for p-image-Edit in ServerNet. The gateway uses this identifier to select the configured route; the developer is PrunaAI.

Where to use p-image-Edit

• Evaluate p-image-Edit on representative visual tasks before selecting it.
• Check dimensions, input image requirements and output format for p-image-Edit.
• Keep the original prompt and task settings so visual results can be reproduced.

Build your integration

A native image route needs a verified input schema, resolution bounds and a price for every billable option. The supported task and route will be documented here when they are ready.

Inputs and service limits

An image model listing does not enable image input on the chat endpoint. Resolution, number of images and editing inputs can change the cost. Do not assume a token price covers the native operation.

A bounded request cost is reserved before sending. The verified tariff or reported provider cost is settled using the exchange rate and sale markup; tax is separate. Media is not billed as chat tokens. Media input must be a valid image or WAV file in a Data URL.

Model-specific native inputs

Input schema snapshot: 2026-10-10. The current gateway execution status is shown above. These catalogue fields help you evaluate the native model; accepted gateway requests are documented in the integration section.

Connect to p-image-Edit API

Enable ai:native on your key and ai:models:read to check availability. Set SERVERNET_API_KEY in your server environment. Change the idempotency key for each new request; keep it unchanged only for an identical retry.

curl https://servernet.cloud/v1/inference \
  -H "Authorization: Bearer $SERVERNET_API_KEY" \
  -H 'Content-Type: application/json' \
  -H 'Idempotency-Key: CHANGE_FOR_EACH_NEW_REQUEST' \
  -d '{
    "model": "di-prunaaip-image-edit-75a811a0a4",
    "prompt": "A futuristic cityscape at sunset, with flying cars and towering skyscrapers.",
    "images": [
        "data:image/png;base64,REPLACE_WITH_YOUR_FILE"
    ]
}'

Use the same Idempotency-Key when retrying an identical request. Successful responses are replayed without a second charge for 24 hours. Do not automatically retry when x-should-retry:false is present. The key is shown once. Store it in a server environment variable. Keep it out of browser code, GitHub and logs.

Compare models for the same task