Pixazo API→Models→HiDream
Pixazo API→Models→HiDream

HiDream O1 API, HiDream O1 Dev API, HiDream I1 Full API: Pricing, Documentation

by HiDream

View as Markdown

HiDream O1 API and its distilled counterpart, the HiDream O1 Dev API, leverage a unified transformer architecture to handle complex text rendering and subject-driven personalization without the need for traditional encoders. Complementing these, the HiDream I1 Full API provides a powerful foundation model focused on delivering production-grade photorealism and superior adherence to intricate instructions. Together, these APIs provide developers with a scalable toolkit for generating professional visual content across various creative and commercial applications.

Get API Key
HiDream API

Models Version

WELCOME BONUS

Get $5 Free Credit on First Payment

No strings attached — add funds and get $5 bonus instantly

Claim Your $5 →

HiDream O1 API Documentation

https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

HiDream O1 Image generate request

Request Code

POST https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}
import requests

url = "https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 50,
    "guidance_scale": 5,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = "https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request";

const data = {
  prompt: "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  image_size: {
    width: 2048,
    height: 2048
  },
  num_inference_steps: 50,
  guidance_scale: 5,
  num_images: 1,
  output_format: "png",
  enable_safety_checker: true
};

fetch(url, {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
  },
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));

curl -X POST "https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 50,
    "guidance_scale": 5,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}'

Output

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

HeaderRequiredDefaultDescription
X-Webhook-URLYes (to enable)—HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed).
X-Webhook-ModeNoterminalterminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - HiDream O1 Image generate request

Parameter Required Type Default Allowed values / range Description
promptYesstring——Text prompt for image generation, editing, or subject-driven personalization. Must describe the desired visual content clearly.
reference_image_urlsNostring[][]—Optional reference images. Use an empty array for text-to-image, one URL for image editing, or multiple URLs for subject-driven personalization.
image_sizeNoenum or {width,height}{"width": 1024, "height": 1024}square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or {width, height} up to 2048x2048Requested output resolution. Accepts a predefined enum (square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9) or an exact size object (e.g. {"width": 2048, "height": 2048}). Dimensions are rounded down to a multiple of 32, up to about 2048x2048 pixels. The default is equivalent to square_hd.
num_inference_stepsNointeger501–50Number of denoising (refinement) steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scaleNofloat50–20Classifier-free guidance scale — controls how closely the output follows your prompt. Higher values stick more strictly to the prompt; lower values allow more creative variation. The full model uses 5.0.
seedNointeger——Random seed for reproducible generation. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
num_imagesNointeger11–4Number of images to generate in a single request.
output_formatNoenumpngjpeg, png, webpThe format of the generated image.
sync_modeNobooleanfalsetrue, falseIf true, the finished image is returned directly as a data URI instead of a download link (and is not stored in request history). Handy for quick tests; for normal use leave it off to get a download link.
enable_safety_checkerNobooleantruetrue, falseEnables the safety checker on generated images (filters unsafe or explicit content). Leave enabled unless you have a specific reason to disable it.
keep_original_aspectNobooleanfalsetrue, falseWhen exactly one reference image is provided, preserves its aspect ratio for the output image instead of using image_size.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image—JPG, PNG, WEBPReference image(s).

Example Request

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}

Response

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'hidream-o1-image' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image_019dxxxx/output.png"],
    "media_type": "image/png"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

HiDream O1 API Pricing

O1 is the production model. O1 Dev is a faster lower-cost preview tier with lower-quality outputs.

Your request will cost $0.01 per image.
Image to Image (Image Editing)

HiDream O1 API Documentation

https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

HiDream O1 Image (Edit) generate request

Request Code

POST https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "reference_image_urls": [
    "https://example.com/model_tests/hidream/woman.png"
  ],
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}
import requests

url = "https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "reference_image_urls": [
        "https://example.com/model_tests/hidream/woman.png"
    ],
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 50,
    "guidance_scale": 5,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = "https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "reference_image_urls": [
    "https://example.com/model_tests/hidream/woman.png"
  ],
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));
curl -X POST "https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "reference_image_urls": [
        "https://example.com/model_tests/hidream/woman.png"
    ],
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 50,
    "guidance_scale": 5,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}'

Output

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

HeaderRequiredDefaultDescription
X-Webhook-URLYes (to enable)—HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed).
X-Webhook-ModeNoterminalterminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image-edit",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - HiDream O1 Image (Edit) generate request

Parameter Required Type Default Allowed values / range Description
promptYesstring——Text prompt describing the desired edit or generation. Must describe the intended result clearly.
reference_image_urlsYesstring[]——Reference images for image editing or subject-driven personalization. Use one image URL for editing, or multiple URLs for multi-subject personalization.
image_sizeNoenum or {width,height}{"width": 2048, "height": 2048}square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or {width, height} up to 2048x2048Requested output resolution. Accepts a predefined enum (square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9) or an exact size object (e.g. {"width": 2048, "height": 2048}). Reference-image outputs use the nearest model-supported resolution, up to about 2048x2048 pixels.
num_inference_stepsNointeger501–50Number of denoising (refinement) steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scaleNofloat50–20Classifier-free guidance scale — controls how closely the output follows your prompt. Higher values stick more strictly to the prompt; lower values allow more creative variation. The full model uses 5.0.
seedNointeger——Random seed for reproducible generation. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
num_imagesNointeger11–4Number of images to generate in a single request.
output_formatNoenumpngjpeg, png, webpThe format of the generated image.
sync_modeNobooleanfalsetrue, falseIf true, the finished image is returned directly as a data URI instead of a download link (and is not stored in request history). Handy for quick tests; for normal use leave it off to get a download link.
enable_safety_checkerNobooleantruetrue, falseEnables the safety checker on generated images (filters unsafe or explicit content). Leave enabled unless you have a specific reason to disable it.
keep_original_aspectNobooleanfalsetrue, falseWhen exactly one reference image is provided, preserves its aspect ratio for the output image instead of using image_size.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image—JPG, PNG, WEBPReference image(s) to edit.

Example Request

{
  "prompt": "Replace the sky with a dramatic sunset and add a flock of birds in the distance",
  "reference_image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/upscaler_019ed0c8-bb34-7854-afbc-b2a164758a15b/output.png"
  ],
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}

Response

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'hidream-o1-image-edit' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image-edit",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image-edit_019dxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

HiDream O1 API Pricing

O1 is the production model. O1 Dev is a faster lower-cost preview tier with lower-quality outputs.

Your request will cost $0.01 per image.
2. HiDream O1 Dev

HiDream O1 Dev API Documentation

https://gateway.pixazo.ai/hidream-o1-image-dev/v1/hidream-o1-image-dev-request

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

HiDream O1 Image (Dev) generate request

Request Code

POST https://gateway.pixazo.ai/hidream-o1-image-dev/v1/hidream-o1-image-dev-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "image_size": {
    "width": 1024,
    "height": 1024
  },
  "num_inference_steps": 28,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}
import requests

url = "https://gateway.pixazo.ai/hidream-o1-image-dev/v1/hidream-o1-image-dev-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "image_size": {
        "width": 1024,
        "height": 1024
    },
    "num_inference_steps": 28,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = "https://gateway.pixazo.ai/hidream-o1-image-dev/v1/hidream-o1-image-dev-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "image_size": {
    "width": 1024,
    "height": 1024
  },
  "num_inference_steps": 28,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));
curl -X POST "https://gateway.pixazo.ai/hidream-o1-image-dev/v1/hidream-o1-image-dev-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "image_size": {
      "width": 1024,
      "height": 1024
    },
    "num_inference_steps": 28,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
  }'

Output

{
  "request_id": "hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

HeaderRequiredDefaultDescription
X-Webhook-URLYes (to enable)—HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed).
X-Webhook-ModeNoterminalterminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image-dev",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image-dev",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - HiDream O1 Image (Dev) generate request

Parameter Required Type Default Allowed values / range Description
promptYesstring——Text prompt for image generation, editing, or subject-driven personalization. Must be at least 1 character — describe the desired visual content clearly.
reference_image_urlsNostring[][] (empty array)—Optional reference images. Use an empty array (or omit) for text-to-image, one URL for image editing, or multiple URLs for subject-driven personalization. URLs must be publicly accessible; base64 data URIs are also accepted.
image_sizeNoenum or {width,height}{width: 1024, height: 1024}square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or a custom {width,height} object up to 2048x2048Output image dimensions. Pass one of the preset enum values, or an object with exact width and height. Dimensions are rounded down to the nearest multiple of 32, up to about 2048x2048. Defaults to 1024x1024.
num_inference_stepsNointeger281–28Number of refinement (denoising) steps. Higher values add detail but take longer. The dev model is distilled for 28 steps — maximum 28; higher values are rejected.
guidance_scaleNofloat0.00–20Classifier-free guidance scale — controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation. The dev model is distilled to run at 0.0.
seedNointeger——Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
num_imagesNointeger11–4Number of images to generate in a single request. Must be between 1 and 4.
output_formatNoenum"png"jpeg, png, webpOutput image format. Allowed values: jpeg, png, webp.
sync_modeNobooleanfalse—If on, the finished image is returned directly (as a data URI) instead of as a download link, and is not kept in request history. Handy for quick tests; for normal use, leave it off to get a download link.
enable_safety_checkerNobooleantrue—Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
keep_original_aspectNobooleanfalse—When exactly one reference image URL is provided, preserve its original aspect ratio instead of conforming to image_size.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image—JPG, PNG, WEBPReference image(s).

Example Request

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "image_size": {
    "width": 1024,
    "height": 1024
  },
  "num_inference_steps": 28,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}

Response

{
  "request_id": "hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'hidream-o1-image-dev' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image-dev",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "hidream-o1-image-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image-dev",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image-dev_019dxxxx/output.png"],
    "media_type": "image/png"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

HiDream O1 Dev API Pricing

Your request will cost $0.005 per image.
Image to Image (Image Editing)

HiDream O1 Dev API Documentation

https://gateway.pixazo.ai/hidream-o1-image-dev-edit/v1/hidream-o1-image-dev-edit-request

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

HiDream O1 Image (Dev Edit) generate request

Request Code

POST https://gateway.pixazo.ai/hidream-o1-image-dev-edit/v1/hidream-o1-image-dev-edit-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "reference_image_urls": [
    "https://example.com/model_tests/hidream/woman.png"
  ],
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 28,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}
import requests

url = "https://gateway.pixazo.ai/hidream-o1-image-dev-edit/v1/hidream-o1-image-dev-edit-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "reference_image_urls": [
        "https://example.com/model_tests/hidream/woman.png"
    ],
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 28,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = "https://gateway.pixazo.ai/hidream-o1-image-dev-edit/v1/hidream-o1-image-dev-edit-request";
const headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "reference_image_urls": [
        "https://example.com/model_tests/hidream/woman.png"
    ],
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 28,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
};

fetch(url, {
    method: "POST",
    headers: headers,
    body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));
curl -X POST "https://gateway.pixazo.ai/hidream-o1-image-dev-edit/v1/hidream-o1-image-dev-edit-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "reference_image_urls": [
        "https://example.com/model_tests/hidream/woman.png"
    ],
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 28,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}'

Output

{
  "request_id": "hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

HeaderRequiredDefaultDescription
X-Webhook-URLYes (to enable)—HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed).
X-Webhook-ModeNoterminalterminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image-dev-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image-dev-edit",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - HiDream O1 Image (Dev Edit) generate request

Parameter Required Type Default Allowed values / range Description
promptYesstring——Text prompt describing the desired edit or generation. Must be at least 1 character — be specific for best results.
reference_image_urlsYesstring[]—At least 1 URLReference images to edit or personalize from. Provide one URL to edit a single image, or multiple URLs for subject-driven personalization. URLs must be publicly accessible; base64 data URIs are also accepted.
image_sizeNoenum or {width,height}{width: 2048, height: 2048}square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or a custom {width,height} object up to 2048x2048Requested output resolution. Pass one of the preset enum values, or an object with exact width and height. Reference-image outputs are snapped to the nearest model-supported resolution, up to about 2048x2048. Defaults to 2048x2048.
num_inference_stepsNointeger281–28Number of refinement (denoising) steps. Higher values add detail but take longer. The dev model is distilled for 28 steps — maximum 28; higher values are rejected.
guidance_scaleNofloat0.00–20Classifier-free guidance scale — controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation. The dev model is distilled to run at 0.0.
seedNointeger——Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
num_imagesNointeger11–4Number of images to generate in a single request. Must be between 1 and 4.
output_formatNoenum"png"jpeg, png, webpOutput image format. Allowed values: jpeg, png, webp.
sync_modeNobooleanfalse—If on, the finished image is returned directly (as a data URI) instead of as a download link, and is not kept in request history. Handy for quick tests; for normal use, leave it off to get a download link.
enable_safety_checkerNobooleantrue—Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
keep_original_aspectNobooleanfalse—When exactly one reference image is provided, preserve its original aspect ratio in the output. If off, the output is resized to match image_size.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image—JPG, PNG, WEBPReference image(s) to edit.

Example Request

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "reference_image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/upscaler_019ed0c8-bb34-7854-afbc-b2a164758a15b/output.png"
  ],
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 28,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}

Response

{
  "request_id": "hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'hidream-o1-image-dev-edit' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image-dev-edit",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image-dev-edit",
  "error": null,
  "output": { "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image-dev-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"], "media_type": "image/png" },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

HiDream O1 Dev API Pricing

Your request will cost $0.005 per image.
3. HiDream I1 Full

HiDream I1 Full API Documentation

https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

HiDream O1 Image generate request

Request Code

POST https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}
import requests

url = "https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 50,
    "guidance_scale": 5,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = "https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request";

const data = {
  prompt: "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  image_size: {
    width: 2048,
    height: 2048
  },
  num_inference_steps: 50,
  guidance_scale: 5,
  num_images: 1,
  output_format: "png",
  enable_safety_checker: true
};

fetch(url, {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
  },
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));

curl -X POST "https://gateway.pixazo.ai/hidream-o1-image/v1/hidream-o1-image-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 50,
    "guidance_scale": 5,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}'

Output

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

HeaderRequiredDefaultDescription
X-Webhook-URLYes (to enable)—HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed).
X-Webhook-ModeNoterminalterminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - HiDream O1 Image generate request

Parameter Required Type Default Allowed values / range Description
promptYesstring——Text prompt for image generation, editing, or subject-driven personalization. Must describe the desired visual content clearly.
reference_image_urlsNostring[][]—Optional reference images. Use an empty array for text-to-image, one URL for image editing, or multiple URLs for subject-driven personalization.
image_sizeNoenum or {width,height}{"width": 1024, "height": 1024}square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or {width, height} up to 2048x2048Requested output resolution. Accepts a predefined enum (square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9) or an exact size object (e.g. {"width": 2048, "height": 2048}). Dimensions are rounded down to a multiple of 32, up to about 2048x2048 pixels. The default is equivalent to square_hd.
num_inference_stepsNointeger501–50Number of denoising (refinement) steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scaleNofloat50–20Classifier-free guidance scale — controls how closely the output follows your prompt. Higher values stick more strictly to the prompt; lower values allow more creative variation. The full model uses 5.0.
seedNointeger——Random seed for reproducible generation. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
num_imagesNointeger11–4Number of images to generate in a single request.
output_formatNoenumpngjpeg, png, webpThe format of the generated image.
sync_modeNobooleanfalsetrue, falseIf true, the finished image is returned directly as a data URI instead of a download link (and is not stored in request history). Handy for quick tests; for normal use leave it off to get a download link.
enable_safety_checkerNobooleantruetrue, falseEnables the safety checker on generated images (filters unsafe or explicit content). Leave enabled unless you have a specific reason to disable it.
keep_original_aspectNobooleanfalsetrue, falseWhen exactly one reference image is provided, preserves its aspect ratio for the output image instead of using image_size.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image—JPG, PNG, WEBPReference image(s).

Example Request

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}

Response

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'hidream-o1-image' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "hidream-o1-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image_019dxxxx/output.png"],
    "media_type": "image/png"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

HiDream I1 Full API Pricing

O1 is the production model. O1 Dev is a faster lower-cost preview tier with lower-quality outputs.

Your request will cost $0.01 per image.
Image to Image (Image Editing)

HiDream I1 Full API Documentation

https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

HiDream O1 Image (Edit) generate request

Request Code

POST https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "reference_image_urls": [
    "https://example.com/model_tests/hidream/woman.png"
  ],
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}
import requests

url = "https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "reference_image_urls": [
        "https://example.com/model_tests/hidream/woman.png"
    ],
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 50,
    "guidance_scale": 5,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = "https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
  "reference_image_urls": [
    "https://example.com/model_tests/hidream/woman.png"
  ],
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));
curl -X POST "https://gateway.pixazo.ai/hidream-o1-image-edit/v1/hidream-o1-image-edit-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field",
    "reference_image_urls": [
        "https://example.com/model_tests/hidream/woman.png"
    ],
    "image_size": {
        "width": 2048,
        "height": 2048
    },
    "num_inference_steps": 50,
    "guidance_scale": 5,
    "num_images": 1,
    "output_format": "png",
    "enable_safety_checker": true
}'

Output

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

HeaderRequiredDefaultDescription
X-Webhook-URLYes (to enable)—HTTPS endpoint on your server that will receive the POST callback. Must respond 2xx within a few seconds (process async if needed).
X-Webhook-ModeNoterminalterminal — fires once at the final status (COMPLETED/FAILED/ERROR). sync — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image-edit",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - HiDream O1 Image (Edit) generate request

Parameter Required Type Default Allowed values / range Description
promptYesstring——Text prompt describing the desired edit or generation. Must describe the intended result clearly.
reference_image_urlsYesstring[]——Reference images for image editing or subject-driven personalization. Use one image URL for editing, or multiple URLs for multi-subject personalization.
image_sizeNoenum or {width,height}{"width": 2048, "height": 2048}square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or {width, height} up to 2048x2048Requested output resolution. Accepts a predefined enum (square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9) or an exact size object (e.g. {"width": 2048, "height": 2048}). Reference-image outputs use the nearest model-supported resolution, up to about 2048x2048 pixels.
num_inference_stepsNointeger501–50Number of denoising (refinement) steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scaleNofloat50–20Classifier-free guidance scale — controls how closely the output follows your prompt. Higher values stick more strictly to the prompt; lower values allow more creative variation. The full model uses 5.0.
seedNointeger——Random seed for reproducible generation. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
num_imagesNointeger11–4Number of images to generate in a single request.
output_formatNoenumpngjpeg, png, webpThe format of the generated image.
sync_modeNobooleanfalsetrue, falseIf true, the finished image is returned directly as a data URI instead of a download link (and is not stored in request history). Handy for quick tests; for normal use leave it off to get a download link.
enable_safety_checkerNobooleantruetrue, falseEnables the safety checker on generated images (filters unsafe or explicit content). Leave enabled unless you have a specific reason to disable it.
keep_original_aspectNobooleanfalsetrue, falseWhen exactly one reference image is provided, preserves its aspect ratio for the output image instead of using image_size.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image—JPG, PNG, WEBPReference image(s) to edit.

Example Request

{
  "prompt": "Replace the sky with a dramatic sunset and add a flock of birds in the distance",
  "reference_image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/upscaler_019ed0c8-bb34-7854-afbc-b2a164758a15b/output.png"
  ],
  "image_size": {
    "width": 2048,
    "height": 2048
  },
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "num_images": 1,
  "output_format": "png",
  "enable_safety_checker": true
}

Response

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'hidream-o1-image-edit' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "hidream-o1-image-edit",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "hidream-o1-image-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "hidream-o1-image-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/hidream-o1-image-edit_019dxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

HiDream I1 Full API Pricing

O1 is the production model. O1 Dev is a faster lower-cost preview tier with lower-quality outputs.

Your request will cost $0.01 per image.