Pixazo APIModelsText to Image APIStudio Ghibli
Pixazo APIModelsText to Image APIStudio Ghibli

Studio Ghibli API: Pricing, Documentation

by Ghibli

Studio Ghibli API, developers can transform text prompts and images into lush, hand-painted-looking scenes with soft lighting, vibrant colors, and the whimsical charm that defines Ghibli animation. The API supports both text-to-image and image-to-image workflows, making it ideal for creative projects, social media content, and applications seeking a distinctive anime art style.

Get API Key
Studio Ghibli 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 →

Studio Ghibli v1 API Documentation

https://gateway.pixazo.ai/studio-ghibli/v1/studio-ghibli/generate

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

Generate Image Request - Studio Ghibli API

Request Code

POST https://gateway.pixazo.ai/studio-ghibli/v1/studio-ghibli/generate
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A peaceful village in the mountains at sunset, Studio Ghibli style"
}
import requests

API_KEY = "your-api-key-here"
BASE_URL = "https://gateway.pixazo.ai/studio-ghibli/v1"

response = requests.post(
    f"{BASE_URL}/studio-ghibli/generate",
    headers={
        "Content-Type": "application/json",
        "Ocp-Apim-Subscription-Key": API_KEY
    },
    json={
        "prompt": "A peaceful village in the mountains at sunset, Studio Ghibli style"
    }
)

result = response.json()
print(result)
async function generateImage() {
  const response = await fetch(
    'https://gateway.pixazo.ai/studio-ghibli/v1/studio-ghibli/generate',
    {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'Ocp-Apim-Subscription-Key': process.env.API_KEY
      },
      body: JSON.stringify({
        prompt: 'A peaceful village in the mountains at sunset, Studio Ghibli style'
      })
    }
  );
  
  const result = await response.json();
  console.log(result);
}

generateImage();
curl -v -X POST "https://gateway.pixazo.ai/studio-ghibli/v1/studio-ghibli/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A peaceful village in the mountains at sunset, Studio Ghibli style"
  }'

Output

{
  "request_id": "studio-ghibli_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/studio-ghibli_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

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": "studio-ghibli_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "studio-ghibli",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/studio-ghibli_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": "studio-ghibli_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "studio-ghibli",
  "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 modePOST 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 - Generate Image Request

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstringText description of the image to generate, rendered in the Studio Ghibli style of this Flux fine-tune. Be specific and descriptive (subject, setting, lighting, mood) for best results.
negative_promptNostring"" (empty)What to exclude from the image, e.g. people, modern buildings, text, watermark. Gateway-only convenience input — the underlying Flux model has no native negative prompt, so it may have limited effect.
imageNostring (URL)Publicly accessible HTTPS image URLInput image for img2img or inpaint mode. When provided, aspect_ratio, width and height are ignored. Omit for plain text-to-image.
maskNostring (URL)Publicly accessible HTTPS image URLImage mask for inpaint mode; requires image. When provided, aspect_ratio, width and height are ignored.
aspect_ratioNostring1:11:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21, customAspect ratio of the generated image. Set to custom to size the image with width and height instead (runs in bf16 mode).
heightNointeger256 – 1440Output height in pixels. Only used when aspect_ratio is custom; rounded to the nearest multiple of 16. Incompatible with go_fast.
widthNointeger256 – 1440Output width in pixels. Only used when aspect_ratio is custom; rounded to the nearest multiple of 16. Incompatible with go_fast.
prompt_strengthNonumber0.80 – 1Prompt strength when using img2img (with image). 1.0 fully replaces the input image; lower values retain more of it.
modelNostringdevdev, schnellWhich base model to run inference with. dev gives the best quality at around 28 steps; schnell is faster and needs only about 4 steps.
num_outputsNointeger11 – 4Number of images to generate in one request. Each output is a separate variation.
num_inference_stepsNointeger281 – 50Number of denoising steps. More steps can add detail but take longer. Use around 28 for dev and about 4 for schnell.
guidance_scaleNonumber30 – 10How closely the image follows the prompt. Lower values look more realistic; good values to try are 2, 2.5, 3 and 3.5.
seedNointegerRandom seed for reproducible generation. Omit for a different random result each time.
output_formatNostringwebpwebp, jpg, pngFormat of the returned image. webp gives the smallest file; png is lossless.
output_qualityNointeger800 – 100Compression quality of the saved file, from 0 (smallest file, lowest quality) to 100 (largest file, best quality). No effect on lossless formats such as PNG.
disable_safety_checkerNobooleanfalsetrue, falseSet to true to disable the safety checker for generated images.
go_fastNobooleanfalsetrue, falseRun faster predictions with a speed-optimised (fp8-quantised) model. Disable to run in original bf16, which is required for custom width/height.
megapixelsNostring11, 0.25Approximate resolution of the generated image, in megapixels.
lora_scaleNonumber1-1 – 3How strongly the main Ghibli LoRA is applied. Sane results are usually between 0 and 1.
extra_loraNostringLoad an additional LoRA. Accepts a hosted model reference (<owner>/<model>, optionally with a version), a HuggingFace URL (huggingface.co/<owner>/<model>), a CivitAI URL, or a direct .safetensors URL.
extra_lora_scaleNonumber1-1 – 3How strongly the extra LoRA (set via extra_lora) is applied. Sane results are usually between 0 and 1.
webhookNostring (URL)HTTPS URLCallback URL notified about this prediction. The gateway POSTs the prediction payload to it as events occur.
webhook_events_filterNoarray of string["start", "output", "logs", "completed"] (all events)start, output, logs, completedWhich events trigger a webhook call, e.g. ["completed"] to be notified only when the prediction finishes. Ignored unless webhook is set.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image1JPG, PNG, WEBPImage (+ optional mask) to Ghibli-fy.

Example Request

{
  "prompt": "A peaceful village in the mountains at sunset, Studio Ghibli style",
  "negative_prompt": "people, modern buildings, cars, text, watermark, realistic photo",
  "aspect_ratio": "16:9",
  "output_format": "png",
  "output_quality": 95
}

Response

{
  "request_id": "studio-ghibli_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/studio-ghibli_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_SUBSCRIPTION_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. Required: $0.01"
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'studio-ghibli' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "studio-ghibli_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "studio-ghibli",
  "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/studio-ghibli_019d42ce-946d-7739-f812-6875c434cb790"

Response (Completed)

{
  "request_id": "studio-ghibli_019d42ce-946d-7739-f812-6875c434cb790",
  "status": "COMPLETED",
  "model_id": "studio-ghibli",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/studio-ghibli_019d42ce-946d-7739-f812-6875c434cb790/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-03-31T07:32:03.749Z",
  "updated_at": "2026-03-31T07:32:20.000Z",
  "completed_at": "2026-03-31T07:32:20.000Z"
}

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 (image/png)
created_atstringWhen request was created
completed_atstring|nullWhen 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.

Studio Ghibli v1 API Pricing

ResolutionPrice (USD)
1024×1024 (1:1)$0.015
1920×1080 (16:9)$0.0297
2560×1096 (21:9)$0.0402
1800×1200 (3:2)$0.0309
1200×1800 (2:3)$0.0309
1080×1350 (4:5)$0.0208
1250×1000 (5:4)$0.0179
1080×1440 (3:4)$0.0222
1440×1080 (4:3)$0.0222
1080×1920 (9:16)$0.0297
1080×2520 (9:21)$0.039

⚡ Performance

Live usage measured on Pixazo's gateway, split by model version. Generation time is how long a generation takes end-to-end (lower is better). Success rate is the percent of generations that complete (higher is better).

Show data for the last
Generations
2,900last 30d
~97 per day
Success rate
89.7%
of completed generations
Generation time
90.2savg
p95 88.5s
Requests
Jul 19max 400Aug 17
Studio Ghibli v1Avg 97/day
Generation Time
Jul 19max 118.0sAug 17
Studio Ghibli v1Avg 91.2s
Error Rate
Jul 19max 66.7%Aug 17
Studio Ghibli v1Avg 10.7%

〰 Uptime

Percent of generations that succeeded over the selected period, per model version.

Avg. Success Rate (30d)
89.66%
across all generations of this model family
Uptime
Jul 19max 100%Aug 17
SuccessfulAvg 89.29%