FLUX 3 Klein · Image Edit

Edit images with FLUX 3 Klein using a text instruction and up to ten reference images. Choose preset or custom output dimensions, request up to four results in one generation, and retrieve the completed images asynchronously.

Developer API pricing

Provider: SeeAPI

USD estimate: $0.0037 / credit · Estimated equivalent, not an additional charge.

1K: 2.2 credits/gen (≈ $0.008/gen, without width)

2K: 3.4 credits/gen (≈ $0.013/gen, without width)

4K: 8.8 credits/gen (≈ $0.033/gen, without width)

Price: 8.8 credits/gen (≈ $0.033/gen, width × height > 4,194,304) | 3.4 credits/gen (≈ $0.013/gen, width × height ≤ 4,194,304) | 2.2 credits/gen (≈ $0.008/gen, width × height ≤ 1,048,576)

Request

POST/v1/generations

AuthorizationSend your API key in the Authorization header using the Bearer scheme.Authorization: Bearer ****************

Header Params

stringrequired

Identifies a generation request so that retries can return the existing generation instead of creating a duplicate.

Required header, up to 255 characters.
Use a new key for each new generation; reuse it only for retries with the exact same request body.

max length: 255

Example:: order-20260818-001

Body Params

application/json

stringrequired

Selects the model that will generate the images.

Required. Use flux-3-klein exactly.

Allowed:flux-3-klein

Default:: flux-3-klein
Example:: flux-3-klein

stringrequired

Selects the image-editing capability.

Required. Use image-edit for this page.

Allowed:image-edit

Default:: image-edit
Example:: image-edit

stringoptional

Selects the public service provider for this generation.

Optional. Use seeapi, or omit this field to use the default provider.

Allowed:seeapi

Default:: seeapi
Example:: seeapi

objectrequired

Contains the reference images, editing instruction, and output image settings for this request.

Required JSON object. Put model parameters inside input.
For custom dimensions, send width and height directly; do not send the Web-only custom_size switch.

Provider parameters

SeeAPIseeapiDefault Provider

array <uri>required

Provides reference images to edit or use as visual guidance.

Required array of 1–10 accessible image URLs.
Supported formats: JPEG, PNG, and WebP; maximum 30 MB per image.
Reference order is preserved. Identify each reference’s role in the prompt when supplying multiple images.
Replace the example URL with your own accessible image URL.

min: 1max: 10min items: 1max items: 10

Example:: ["https://client.example.com/input.png"]

stringrequired

Describes the changes to make and the elements to preserve.

Required, 1–5,000 characters.
When using multiple reference images, identify their roles clearly in your instruction.
enhance_prompt controls whether the instruction may be refined.

min length: 1max length: 5000

Example:: Change the teapot to matte blue while keeping its shape, lighting, and background unchanged.

stringoptional

Sets the preset width-to-height proportion of the output image.

Optional; defaults to auto for automatic aspect-ratio selection. Choose auto or one of the listed ratios.
Ignored when width and height are both supplied.

Allowed:auto1:14:33:43:22:316:99:1621:99:21

Default:: auto

stringoptional

Selects the output resolution for preset-size generation.

Optional; defaults to 1K. Supported values are 1K, 2K, and 4K.
Ignored when width and height are both supplied; custom-size pricing is based on their product.
See the current model pricing for applicable rates.

Allowed:1K2K4K

Default:: 1K

numberoptional

Sets the exact output image width in pixels.

Optional integer from 256 to 4096 pixels, inclusive. Supply height together with width.
Both dimensions must be within 256–4096 pixels, and 0.4 ≤ width / height ≤ 2.5.
When both are supplied, aspect_ratio and resolution are ignored.
Custom-size pricing is based on width × height: up to 1,048,576 pixels uses the 1K tier; more than 1,048,576 and up to 4,194,304 pixels uses the 2K tier; larger sizes use the 4K tier.
Total charge = current price per image × num_output_images. See the current model pricing for applicable rates.

min: 256max: 4096

numberoptional

Sets the exact output image height in pixels.

Optional integer from 256 to 4096 pixels, inclusive. Supply width together with height.
Both dimensions must be within 256–4096 pixels, and 0.4 ≤ width / height ≤ 2.5.
When both are supplied, aspect_ratio and resolution are ignored.
Custom-size pricing is based on width × height: up to 1,048,576 pixels uses the 1K tier; more than 1,048,576 and up to 4,194,304 pixels uses the 2K tier; larger sizes use the 4K tier.
Total charge = current price per image × num_output_images. See the current model pricing for applicable rates.

min: 256max: 4096

stringoptional

Selects the file format of the generated images.

Optional; defaults to png. Supported values are png, jpeg, and webp.

Allowed:pngjpegwebp

Default:: png

numberoptional

Sets how many output images to request in one generation.

Optional integer from 1 to 4; defaults to 1.
Multiple images belong to one generation, not separate generation requests.
Total charge = current price per image × num_output_images. See the current model pricing for applicable rates.

min: 1max: 4

Default:: 1

numberoptional

Controls the random seed used during image generation.

Optional integer from 0 to 2147483647, inclusive; 0 is valid.
Omit it to let the model choose a random seed.

min: 0max: 2147483647

booleanoptional

Controls whether the model expands or refines your prompt before generating images.

Optional boolean; defaults to true.
Set false to disable prompt enhancement. Use JSON true or false, not quoted strings.

Default:: true

booleanoptional

Controls whether the content safety check is enabled for this generation.

Optional boolean; defaults to false.
Set true to enable the check. Use JSON true or false, not quoted strings.

Default:: false

string <uri>optional

Specifies the endpoint that receives a webhook when the generation succeeds or fails.

Optional absolute HTTPS URL, up to 2,048 characters.
Replace the example URL with your own webhook endpoint and verify webhook signatures before trusting notifications.
If omitted, use the task details endpoint to poll for results.

max length: 2048

Example:: https://client.example.com/webhooks/seeapi

Responses

202The generation has been accepted for asynchronous processing. Save generation.id to query its status and retrieve the completed images.

Bodyapplication/json

This response is an acknowledgement, not the final image result.

objectrequired

stringrequired

Unique generation ID. Use this ID with the task details endpoint.

Example:: task_xxx

stringrequired

Example:: flux-3-klein

stringrequired

Example:: image-edit

stringrequired

Allowed:seeapi

seeapi: SeeAPI

Example:: seeapi

stringrequired

Current processing status. Retrieve task details to check for completion or failure.

Allowed:processing

Example:: processing

numberrequired

Estimated credits for this request, including the requested image count.

Example:: 2.2

numberrequired

Credits charged to this generation. Check the latest task details for the current amount.

Example:: 0

numberrequired

Credits refunded for this generation, if any.

Example:: 0

string <date-time>required

Example:: 2026-08-18T10:00:00Z

string <date-time>required

Example:: 2026-08-18T10:00:00Z

booleanrequired

Whether this response is an idempotent replay of an earlier request.

Example:: false

200An existing generation was returned for an idempotent retry. Use the returned generation ID instead of creating another request.

Bodyapplication/json

objectrequired

stringrequired

Unique generation ID. Use this ID with the task details endpoint.

Example:: task_xxx

stringrequired

Example:: flux-3-klein

stringrequired

Example:: image-edit

stringrequired

Allowed:seeapi

seeapi: SeeAPI

Example:: seeapi

stringrequired

Current processing status. Retrieve task details to check for completion or failure.

Allowed:processing

Example:: processing

numberrequired

Estimated credits for this request, including the requested image count.

Example:: 2.2

numberrequired

Credits charged to this generation. Check the latest task details for the current amount.

Example:: 0

numberrequired

Credits refunded for this generation, if any.

Example:: 0

string <date-time>required

Example:: 2026-08-18T10:00:00Z

string <date-time>required

Example:: 2026-08-18T10:00:00Z

booleanrequired

Whether this response is an idempotent replay of an earlier request.

Example:: false

400

Invalid JSON, parameters, Schema, or API Policy

401

Invalid API Key or authentication failed

402

Insufficient credits

403

The current request is not allowed

404

Model, Endpoint, or task not found

409

Idempotency conflict or the same request is still being created

413

Request body is too large

429

Too many requests

503

Service temporarily unavailable

Query Task Status

After submitting a task, use the unified query endpoint to check progress and retrieve results:

Get Task DetailsLearn how to query task status and retrieve generation results

Use a webhook for completion notifications, or poll the task until it reaches a terminal status.

Note

Wait for a successful terminal status before reading the output image URLs. For a failed task, inspect its error details before deciding whether to retry.

Related Resources

Market Overview

Explore all available models

Credits & Billing

View credit balance, plans, and billing activity

Usage

Review API usage and credit consumption

Callbacks

Manage the secret used to verify generation webhook signatures. Callback URLs are supplied when you create each generation.

Webhook flow

Callback URL per generation.

Webhook signing key

Code Examples

Request

const response = await fetch("https://api.seeapi.com/v1/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Idempotency-Key": "order-20260818-001",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
  "model": "flux-3-klein",
  "endpoint": "image-edit",
  "provider": "seeapi",
  "input": {
    "input_images": [
      "https://client.example.com/input.png"
    ],
    "prompt": "Change the teapot to matte blue while keeping its shape, lighting, and background unchanged.",
    "aspect_ratio": "auto",
    "resolution": "1K",
    "output_format": "png",
    "num_output_images": 1,
    "enhance_prompt": true,
    "nsfw_checker": false
  },
  "callback_url": "https://client.example.com/webhooks/seeapi"
})
});

const result = await response.json();

ResponseHTTP 202

{
  "generation": {
    "id": "task_xxx",
    "model": "flux-3-klein",
    "endpoint": "image-edit",
    "provider": "seeapi",
    "status": "processing",
    "estimated_credits": 2.2,
    "consumed_credits": 0,
    "refunded_credits": 0,
    "created_at": "2026-08-18T10:00:00Z",
    "updated_at": "2026-08-18T10:00:00Z"
  },
  "idempotent": false
}

const response = await fetch("https://api.seeapi.com/v1/generations", { method: "POST", headers: { "Authorization": "Bearer YOUR_API_KEY", "Idempotency-Key": "order-20260818-001", "Content-Type": "application/json" }, body: JSON.stringify({ "model": "flux-3-klein", "endpoint": "image-edit", "provider": "seeapi", "input": { "input_images": [ "https://client.example.com/input.png" ], "prompt": "Change the teapot to matte blue while keeping its shape, lighting, and background unchanged.", "aspect_ratio": "auto", "resolution": "1K", "output_format": "png", "num_output_images": 1, "enhance_prompt": true, "nsfw_checker": false }, "callback_url": "https://client.example.com/webhooks/seeapi" }) }); const result = await response.json();

{ "generation": { "id": "task_xxx", "model": "flux-3-klein", "endpoint": "image-edit", "provider": "seeapi", "status": "processing", "estimated_credits": 2.2, "consumed_credits": 0, "refunded_credits": 0, "created_at": "2026-08-18T10:00:00Z", "updated_at": "2026-08-18T10:00:00Z" }, "idempotent": false }

Responses

202The generation has been accepted for asynchronous processing. Save generation.id to query its status and retrieve the completed images.

Bodyapplication/json

This response is an acknowledgement, not the final image result.

objectrequired

stringrequired

Unique generation ID. Use this ID with the task details endpoint.

Example:: task_xxx

stringrequired

Example:: flux-3-klein

stringrequired

Example:: image-edit

stringrequired

Allowed:seeapi

seeapi: SeeAPI

Example:: seeapi

stringrequired

Current processing status. Retrieve task details to check for completion or failure.

Allowed:processing

Example:: processing

numberrequired

Estimated credits for this request, including the requested image count.

Example:: 2.2

numberrequired

Credits charged to this generation. Check the latest task details for the current amount.

Example:: 0

numberrequired

Credits refunded for this generation, if any.

Example:: 0

string <date-time>required

Example:: 2026-08-18T10:00:00Z

string <date-time>required

Example:: 2026-08-18T10:00:00Z

booleanrequired

Whether this response is an idempotent replay of an earlier request.

Example:: false

200An existing generation was returned for an idempotent retry. Use the returned generation ID instead of creating another request.

Bodyapplication/json

objectrequired

stringrequired

Unique generation ID. Use this ID with the task details endpoint.

Example:: task_xxx

stringrequired

Example:: flux-3-klein

stringrequired

Example:: image-edit

stringrequired

Allowed:seeapi

seeapi: SeeAPI

Example:: seeapi

stringrequired

Current processing status. Retrieve task details to check for completion or failure.

Allowed:processing

Example:: processing

numberrequired

Estimated credits for this request, including the requested image count.

Example:: 2.2

numberrequired

Credits charged to this generation. Check the latest task details for the current amount.

Example:: 0

numberrequired

Credits refunded for this generation, if any.

Example:: 0

string <date-time>required

Example:: 2026-08-18T10:00:00Z

string <date-time>required

Example:: 2026-08-18T10:00:00Z

booleanrequired

Whether this response is an idempotent replay of an earlier request.

Example:: false

400

Invalid JSON, parameters, Schema, or API Policy

401

Invalid API Key or authentication failed

402

Insufficient credits

403

The current request is not allowed

404

Model, Endpoint, or task not found

409

Idempotency conflict or the same request is still being created

413

Request body is too large

429

Too many requests

503

Service temporarily unavailable