Create an image edit

POST/v1/images/edits

Create an image edit.

Compatible with OpenAI's create-image-edit endpoint: send one or more source images and a prompt as multipart/form-data and get the edited images back. Send a single image as image, or several (up to 16) as repeated image[] parts, as the OpenAI SDKs do for a list. Each image must have an image/* content type. model, prompt and at least one image are required, and n must be an integer; otherwise a 400. OpenAI credentials only; any other provider is a 422.

Authenticate with a BYOK virtual key or with x-provider and x-api-key; a PLATFORM virtual key is a 400. The key's checks, the plan's limits and the organization's approved-provider policy (403) apply. Without x-retry-count a failed call is retried up to 3 times on 429 and 5xx.

Authorization

AuthorizationBearer <slug>.<secret>
A virtual key's API key (vk-....<secret>), as Authorization: Bearer. What the OpenAI SDK sends from its api_key. Used by the inference endpoints.
orx-virtual-keyheader
A virtual key's API key in the x-virtual-key header, for clients that keep Authorization for something else.
orx-api-keyheader
Direct credentials: the provider's own API key in x-api-key, with the provider named in x-provider (for example openai). On /v1/messages a virtual key is accepted in x-api-key too, which is what the Claude SDK sends.

Headers

x-providerstring
With direct credentials: the provider x-api-key belongs to, for example openai or anthropic (case and dashes are normalised). Not used with a virtual key.
x-retry-countinteger<int32>
How many times to retry a failed provider call, 0 to 5. Without the header, chat completions, Claude Messages and prompt completions do not retry, and the other endpoints retry up to 3 times. Retries back off exponentially from 1 second and honour a numeric Retry-After. The number made is in the x-retry-count response header.
x-retry-status-codesstring
Comma-separated provider status codes to retry on. Default 429,500,502,503,504,529.

Request body multipart/form-data

imagestring<binary>
The image to edit. Send several as repeated image[] parts instead.
image[]string<binary>
One of several images to edit (gpt-image models, up to 16).
maskstring<binary>
Optional mask whose fully transparent areas mark where the image is edited.
promptstring
A text description of the edit.
modelstring
The image model, for example gpt-image-1 or dall-e-2.
ninteger
How many images to generate. Optional; the provider's default otherwise.
sizestring
The size of the generated images, for example 1024x1024. Optional.
response_formatstring
url or b64_json: how the images are returned. Optional.

Responses

200application/json

createdinteger<int64>
When the images were created, as a Unix timestamp in seconds.
dataobject[]
The images, one per n requested.
Child attributes
- urlstring
  A URL to download the image from, when response_format is url. The provider's URL, valid for a limited time.
- b64_jsonstring
  The image as base64-encoded data, when response_format is b64_json (always, for the gpt-image models).
- revised_promptstring
  The prompt the model actually used, when it rewrote yours (dall-e-3). Absent otherwise.

Request

curl -X POST "https://api.vectoraxis.ai/v1/images/edits" \
  -H "Authorization: Bearer $VECTORAXIS_VIRTUAL_KEY" \
  -F "image=@./file" \
  -F "image[]=@./file" \
  -F "mask=@./file" \
  -F "prompt=string" \
  -F "model=string" \
  -F "n=0" \
  -F "size=string" \
  -F "response_format=string"

VectorAxis is built by GK Labs, a member of NVIDIA Inception.