Bypass OpenAI image edits

Native protocol and authentication

Use an XHub public model name and virtual key with the matching Bypass deployment. XHub maps the model and injects deployment credentials, preserves native fields and enforces access and billing. Bypass does not run the standard pre-call text guardrail chain. Send Authorization: Bearer $XHUB_API_KEY. Model availability depends on configured deployments.

Overview

Image edits

Behavior

Let curl set multipart boundaries. Some native deployments accept JSON references instead; use the matching protocol.

Endpoint and authentication

POST /bypass/openai/v1/images/edits

Use an XHub API key: Authorization: Bearer . Do not use upstream provider credentials as gateway keys.

Use the gateway root Base URL shown in the playground, without appending /v1; send requests to the full endpoint path above.

Request example

curl "$XHUB_BASE_URL/bypass/openai/v1/images/edits" \
  -H "Authorization: Bearer $XHUB_API_KEY" \
  -F "model=YOUR_MODEL_NAME" -F "image=@source.png" \
  -F "prompt=Add a small lighthouse."

Request parameters

Field	Type	Description
model	string · required	Public model name; deployment must support this protocol.
image	file	array · required
prompt / mask	string / file	Edit instruction and optional mask.

Success response

{
  "data": [
    {
      "b64_json": "BASE64_IMAGE_DATA"
    }
  ]
}

Field	Type
data	object[]
data[].b64_json	string

Errors and troubleshooting

HTTP	Meaning
400	Invalid request. Check JSON, parameters and query.
401	Missing or invalid XHub credential.
403	Permission denied. Check model scope or policy.
429	Limit exceeded. Inspect response details and Retry-After.