Generate images from a text prompt

POST

/v1/images/generations

package main

import (
  "fmt"
  "strings"
  "net/http"
  "io"
)

func main() {

  url := "https://api.ai.wpengine.com/v1/images/generations"

  payload := strings.NewReader("{ \"model\": \"google/gemini-2.5-flash-image\", \"prompt\": \"example\", \"n\": 1, \"size\": \"1024x1024\" }")

  req, _ := http.NewRequest("POST", url, payload)

  req.Header.Add("Authorization", "Bearer <token>")
  req.Header.Add("Content-Type", "application/json")

  res, _ := http.DefaultClient.Do(req)

  defer res.Body.Close()
  body, _ := io.ReadAll(res.Body)

  fmt.Println(res)
  fmt.Println(string(body))

}

const url = 'https://api.ai.wpengine.com/v1/images/generations';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"google/gemini-2.5-flash-image","prompt":"example","n":1,"size":"1024x1024"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}

<?php

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.ai.wpengine.com/v1/images/generations', [
  'body' => '{ "model": "google/gemini-2.5-flash-image", "prompt": "example", "n": 1, "size": "1024x1024" }',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();

curl --request POST \
  --url https://api.ai.wpengine.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "model": "google/gemini-2.5-flash-image", "prompt": "example", "n": 1, "size": "1024x1024" }'

Requires a valid WP Engine bearer token. API keys must carry the “image:write” permission.

Authorizations

bearerAuth

Request Body^required

application/json

object

model

required

Model identifier in “provider/model-name” format (e.g. “google/gemini-2.5-flash-image”).

string

Example

google/gemini-2.5-flash-image

prompt

required

Text prompt describing the desired image.

string

Number of images to generate (1-4).

integer

default: 1 >= 1 <= 4

size

Image dimensions (e.g. “1024x1024”, “1024x1792”, “1792x1024”).

string

Example

1024x1024

Responses

200

Generated images

application/json

object

created

required

Unix timestamp.

integer format: int64

data

required

Array<object>

object

b64_json

required

Base64-encoded image data.

string

revised_prompt

The prompt as revised by the model (may differ from the input).

string

Example^generated

{
  "created": 1,
  "data": [
    {
      "b64_json": "example",
      "revised_prompt": "example"
    }
  ]
}

400

Invalid request body or parameters. On agent create and update, error type “profile_unavailable” means the requested profile is not available to the caller.

application/json

object

error

required

object

message

required

string

type

required

string

error_code

Stable, machine-readable cause, set by routes that document their codes (the AI readiness routes); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

code

required

integer

request_id

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

Example

{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

401

Missing or invalid bearer token

application/json

object

error

required

object

message

required

string

type

required

string

error_code

string

code

required

integer

request_id

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

Example

{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

Headers

WWW-Authenticate

string

Example

Bearer realm="ai-services"

402

The account’s credit balance is exhausted. Grant or top up credits before retrying. Distinct from 429, which is edge rate limiting.

application/json

object

error

required

object

message

required

string

type

required

string

error_code

string

code

required

integer

request_id

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

Example

{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

403

The token is valid, but the request is forbidden. Error type “permission_error” means the token’s scope/permission is insufficient or the authenticated user is not authorized for the target account; “entitlement_required” means the account lacks the required product entitlement; and “account_required” means no billing account could be resolved. On /v1/chat/completions when content moderation is enabled, and on /v1/sessions/{session_id}/events, error type “content_policy_violation” instead means the request content was blocked by content moderation policy; that response never identifies which filter or category matched.

application/json

object

error

required

object

message

required

string

type

required

string

error_code

string

code

required

integer

request_id

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

Example

{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

413

Request body exceeds the 64 KiB limit

application/json

object

error

required

object

message

required

string

type

required

string

error_code

string

code

required

integer

request_id

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

Example

{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

429

Rate limit exceeded. The request was throttled at the edge; wait and retry later. The response body is a short HTML page generated by the load balancer, not a structured JSON error — clients should rely on the 429 status code rather than parsing the body.

text/html

string

502

Upstream provider returned an error

application/json

object

error

required

object

message

required

string

type

required

string

error_code

string

code

required

integer

request_id

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

Example

{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

503

A required dependency is temporarily unavailable. Retry after a short delay with exponential back-off. An entitlement lookup failure uses error type “entitlement_unavailable”.

application/json

object

error

required

object

message

required

string

type

required

string

error_code

string

code

required

integer

request_id

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

Example

{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

default

Upstream provider error passed through with its original status code and response body. The shape may vary by provider.

application/json

object

error

required

object

message

required

string

type

required

string

error_code

string

code

required

integer

request_id

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

Example

{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}

Thanks for the feedback!

Platforms

Product Extensions

Plugins

Tools

Was this helpful?

Generate images from a text prompt

Authorizations

Request Body^required

Example

Example

Responses

200

Example^generated

400

Example

401

Example

Headers

Example

402

Example

403

Example

413

Example

429

502

Example

503

Example

default

Example

Was this helpful?

Authorizations

Request Bodyrequired

Example

Example

Responses

200

Examplegenerated

400

Example

401

Example

Headers

Example

402

Example

403

Example

413

Example

429

502

Example

503

Example

default

Example

Was this helpful?

Request Body^required

Example^generated