Flux 3 API documentation
Integrate Flux 3 with your VezAPI key. The operations below share the same authentication and account balance.
https://api.vezapi.comSend Authorization: Bearer YOUR_VEZAPI_KEY. Use a unique Idempotency-Key for each submission; reuse it only when checking the same request.
FLUX 3 Klein Edit Image
/api/v1/jobs/createTaskModel IDs: flux-3/klein-edit-image
| Parameter | Type | Description & constraints |
|---|---|---|
modelrequired | string | The model name used for generation. This endpoint must use `flux-3/klein-edit-image`. Values: Default: |
callBackUrloptional | string | The URL to receive generation task completion updates. Optional but recommended for production use. The system POSTs the task status and results to this URL when generation completes. To ensure callback security, see [Webhook Verification Guide](/common-api/webhook-verification). |
inputrequired | object | Input parameters for the generation task |
input.promptrequired | string | An instruction describing how to edit the image (Max length: 5000 characters)
|
input.image_urlsrequired | array | Input images to transform or use as reference (supports up to 10 images) (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 30.0MB)
|
input.aspect_ratiooptional | string | Aspect ratio of the generated image. Select auto to match the first input image ratio. Options: 1:1; 4:3; 3:4; 3:2; 2:3; 16:9; 9:16; 21:9; 9:21; auto Values: Default: |
input.resolutionoptional | string | Resolution of the generated image Options: 1K; 2K; 4K Values: Default: |
input.widthoptional | integer | Width of the generated image. Both width and height must be passed at the same time. Must be an integer between 256 and 4096. The aspect ratio (width:height) must be between 1:2.5 and 2.5:1. Once passed, aspect_ratio and resolution are ignored.
|
input.heightoptional | integer | Height of the generated image. Both width and height must be passed at the same time. Must be an integer between 256 and 4096. The aspect ratio (width:height) must be between 1:2.5 and 2.5:1. Once passed, aspect_ratio and resolution are ignored.
|
input.output_formatoptional | string | Format of the output image Options: png; jpeg; webp Values: Default: |
input.num_imagesoptional | integer | Number of images to generate Default:
|
input.seedoptional | integer | Random seed
|
input.enhance_promptoptional | boolean | Rewrites the prompt into a fuller description before generating, which noticeably improves quality. Enabled by default (also when the parameter is omitted); pass false to turn it off. Applies to both text-to-image and image editing; in editing, the rewrite preserves the intent of the original instruction. Values: Default: |
input.nsfw_checkeroptional | boolean | Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model. |
Request example
curl -X POST 'https://api.vezapi.com/api/v1/jobs/createTask' \
-H 'Authorization: Bearer YOUR_VEZAPI_KEY' \
-H 'Idempotency-Key: your-unique-request-id' \
-H 'Content-Type: application/json' \
-d '{
"model": "flux-3/klein-edit-image",
"input": {
"prompt": "Your prompt",
"image_urls": [
"Your prompt"
],
"aspect_ratio": "auto",
"resolution": "1K"
}
}'Responses and errors
HTTP 200
Request Successful
| Parameter | Type | Description & constraints |
|---|---|---|
codeoptional | integer | Status code of the request. The HTTP status is 200 even when the request fails, so always check this field: 200 means success; any other value means the request failed and msg describes the reason. Common values: 401 invalid or missing API key; 402 insufficient credits; 429 rate limit exceeded; 422 or 500 the request could not be processed (read msg and check your parameters before retrying). Values: |
msgoptional | string | Response message, error description upon failure |
datarequired | object | |
data.taskIdrequired | string | The task ID can be used with the "Get Task Details" endpoint to query the task status. |
FLUX 3 Klein Text to Image
/api/v1/jobs/createTaskModel IDs: flux-3/klein-text-to-image
| Parameter | Type | Description & constraints |
|---|---|---|
modelrequired | string | The model name used for generation. This endpoint must use `flux-3/klein-text-to-image`. Values: Default: |
callBackUrloptional | string | The URL to receive generation task completion updates. Optional but recommended for production use. The system POSTs the task status and results to this URL when generation completes. To ensure callback security, see [Webhook Verification Guide](/common-api/webhook-verification). |
inputrequired | object | Input parameters for the generation task |
input.promptrequired | string | A text description of the image you want to generate (Max length: 5000 characters)
|
input.aspect_ratiooptional | string | Aspect ratio of the generated image Options: 1:1; 4:3; 3:4; 3:2; 2:3; 16:9; 9:16; 21:9; 9:21 Values: Default: |
input.resolutionoptional | string | Resolution of the generated image Options: 1K; 2K; 4K Values: Default: |
input.widthoptional | integer | Image width. Both width and height must be passed at the same time. Aspect ratio must be between 1:2.5 and 2.5:1. Once passed, aspect_ratio and resolution are ignored.
|
input.heightoptional | integer | Image height. Both width and height must be passed at the same time. Aspect ratio must be between 1:2.5 and 2.5:1. Once passed, aspect_ratio and resolution are ignored.
|
input.output_formatoptional | string | Format of the output image Options: png; jpeg; webp Values: Default: |
input.num_imagesoptional | integer | Number of images to generate Default:
|
input.seedoptional | integer | Random seed
|
input.enhance_promptoptional | boolean | Rewrites the prompt into a fuller description before generating, which noticeably improves quality. Enabled by default (also when the parameter is omitted); pass false to turn it off. Applies to both text-to-image and image editing; in editing, the rewrite preserves the intent of the original instruction. Values: Default: |
input.nsfw_checkeroptional | boolean | Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model. |
Request example
curl -X POST 'https://api.vezapi.com/api/v1/jobs/createTask' \
-H 'Authorization: Bearer YOUR_VEZAPI_KEY' \
-H 'Idempotency-Key: your-unique-request-id' \
-H 'Content-Type: application/json' \
-d '{
"model": "flux-3/klein-text-to-image",
"input": {
"prompt": "Your prompt",
"aspect_ratio": "1:1",
"resolution": "1K"
}
}'Responses and errors
HTTP 200
Request Successful
| Parameter | Type | Description & constraints |
|---|---|---|
codeoptional | integer | Status code of the request. The HTTP status is 200 even when the request fails, so always check this field: 200 means success; any other value means the request failed and msg describes the reason. Common values: 401 invalid or missing API key; 402 insufficient credits; 429 rate limit exceeded; 422 or 500 the request could not be processed (read msg and check your parameters before retrying). Values: |
msgoptional | string | Response message, error description upon failure |
datarequired | object | |
data.taskIdrequired | string | The task ID can be used with the "Get Task Details" endpoint to query the task status. |
Task status and callbacks
For asynchronous tasks, keep the returned taskId. Query GET /api/v1/jobs/recordInfo?taskId=... or provide callBackUrl when creating the task. Only the account that created a task can access it or derive new resources from it.
A timeout can mean the submission was accepted. Inspect the existing request in your dashboard; do not create another task automatically. Callback delivery is retried and may arrive more than once. Deduplicate with X-VezAPI-Event-Id.
Files, logs and billing
Generated media normally follows a 14-day provider lifetime; uploaded files expire after 24 hours. Save the files you need before expiration. VezAPI streams registered files without keeping a permanent media library. Request logs are retained for two calendar months.
Credits are reserved before submission. Final deductions match actual discounted consumption one for one. Unknown usage pauses new paid requests. If available funds cannot cover final usage while protecting other reservations, settlement stays pending until funded; model usage cannot make the wallet negative. Time-based inputs require server-side metadata reads; a failed read prevents submission.