Image Generation

P-H3-Image API

P-H3-Image: open-weights image model built from MiniMax H3. Photoreal, editorial and film-still looks up to 8 MP, short quoted text, and edits from up to 8 images. Integrate this model via REST with endpoint docs, parameters, and code examples.

Prompting guide Compare image models Use cases

Img2Img

Editing

Credit Cost

1 credit

Type

Image

Get API Key

Create auth keys for apps and agents

See Usage

Track requests, credits, and logs

Buy Credits

Top up prepaid API capacity

API Endpoint

POST

/api/v1/models/p-h3-image/run

Test This Model

Run a real request through the API pipeline and inspect the exact input and output your integration will handle. Uses your credits like any API call; failed runs are refunded automatically.

LLM.txt

AI-Ready

For AI assistants

Copy this model's documentation into Claude, GPT, or any AI for instant integration help.

/llm/p-h3-image.txt

OpenAPI Spec

Swagger compatible

Import into Postman, Swagger UI, or generate client SDKs in any language.

/api/openapi

Parameters

Input parameters accepted by this model

Parameter	Type	Description	Default
`prompt` required	string	What to generate, or the edit to make to image 1 (refer to the others as picture 2, picture 3, ...)	-
`aspect_ratio`	enum	"auto" keeps the shape of image 1 when editing, else 1:1 `auto1:14:33:43:2`+3 more	`auto`
`resolution`	enum	1k (about 1 megapixel, 0.5 credits per image), 2k (about 4 megapixels, 1 credits) or 4k (about 8 megapixels, the sharpest, 1.5 credits) `1k2k4k`	`2k`
`num_images`	integer	Images to generate (1-4) min: 1 \| max: 4	`1`
`reference_images`	array	Up to 8 image URLs. The first is the image to edit; the others are references the prompt can name as picture 2, picture 3, ...	-
`prompt_upsampling`	boolean	Rewrite the prompt into the detailed form the model renders best (on by default). Turn it off only when you send a complete prompt yourself.	`true`
`seed`	integer	Random seed for reproducibility	-
`output_format`	enum	jpeg, png or webp `jpegpngwebp`	`jpeg`

Use saved characters (@Name)

Write @Name in the prompt to use a character, product, outfit, location, prop or style saved in the account's Character Studio, for example "@Mara on a beach at sunset". Its photos are added to reference_images automatically, after any images you send yourself, so your own image numbering is unchanged. List saved names with GET /api/v1/characters and save new ones with POST /api/v1/characters. An @word that names nothing saved stays plain text.

Supported Aspect Ratios

1:1

4:3

3:4

3:2

2:3

16:9

9:16

Code Examples

Generate with P-H3-Image: copy and paste to get started

bash

curl -X POST "https://pixeldojo.ai/api/v1/models/p-h3-image/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A documentary photograph of a fishmonger laughing behind a crowded ice counter at dawn, steam in the cold air",
    "aspect_ratio": "3:2"
  }'

Response Format

Submit Response (202 Accepted)

json

{
  "jobId": "job_abc123...",
  "status": "pending",
  "statusUrl": "https://pixeldojo.ai/api/v1/jobs/job_abc123...",
  "creditCost": 1,
  "creditsRemaining": 95,
  "expiresAt": "2026-11-05T02:13:20Z"
}

Completed Response