## Basic model info - Model name: minimax/minimax minimax-h3-image-highspeed - Model description: MiniMax H3 Image Highspeed is the lower-latency tier for high-throughput image generation and editing, with the same 20-megapixel output ceiling, 10-output batching, and 16-reference-image composition support. - Endpoint name: image-editing ## Model schema The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/minimax/minimax-h3-image-highspeed/a5de3f0ac9fefd6e6d291f0105d486b4f8b7970e.json) ### Model input schema The model input schema is: ```json { "additionalProperties": false, "properties": { "prompt": { "description": "Generation or editing instruction. Up to 32,000 characters.", "maxLength": 32000, "minLength": 1, "title": "Prompt", "type": "string", "x-sr-order": 201 }, "width": { "anyOf": [ { "maximum": 14142, "minimum": 1, "type": "integer" }, { "type": "null" } ], "description": "Optional output width. Omit both dimensions to use fal auto sizing.", "title": "Width", "x-sr-order": 402 }, "height": { "anyOf": [ { "maximum": 14142, "minimum": 1, "type": "integer" }, { "type": "null" } ], "description": "Optional output height. Omit both dimensions to use fal auto sizing.", "title": "Height", "x-sr-order": 403 }, "images": { "description": "One to sixteen images to edit or compose, in the order referenced by the prompt. Every side must be 128–8192 pixels.", "items": { "anyOf": [ { "format": "uri", "maxLength": 2083, "minLength": 1, "type": "string" }, { "type": "string" } ] }, "maxItems": 16, "minItems": 1, "title": "Images", "type": "array", "x-sr-order": 301 }, "n": { "default": 1, "description": "Number of images to generate. Every image contributes token usage.", "maximum": 10, "minimum": 1, "title": "N", "type": "integer", "x-sr-order": 401 }, "output_format": { "default": "png", "description": "Generated image encoding.", "enum": [ "jpeg", "png", "webp", "jpg" ], "title": "Output Format", "type": "string", "x-sr-order": 404 } }, "required": [ "prompt", "images" ], "title": "ImageEditingInput", "type": "object" } ``` ### Model output schema The model output schema is: ```json { "properties": { "actual_prompt": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Expanded prompt when supplied by the provider.", "title": "Actual Prompt" }, "has_nsfw_concepts": { "description": "Safety flag for each generated image.", "items": { "type": "boolean" }, "title": "Has Nsfw Concepts", "type": "array" }, "images": { "items": { "properties": { "content_type": { "description": "The mime type of the file.", "title": "Content Type", "type": "string" }, "file_name": { "description": "The name of the file. It will be auto-generated if not provided.", "title": "File Name", "type": "string" }, "file_size": { "description": "The size of the file in bytes.", "title": "File Size", "type": "integer" }, "url": { "description": "The URL where the file can be downloaded from.", "title": "Url", "type": "string" } }, "required": [ "content_type", "file_name", "file_size", "url" ], "title": "SunraFile", "type": "object" }, "title": "Images", "type": "array" }, "timings": { "additionalProperties": { "type": "number" }, "description": "Provider timing metrics in seconds.", "title": "Timings", "type": "object" }, "units": { "description": "Authoritative fal cost in USD: x-fal-billable-units × $0.001.", "exclusiveMinimum": 0, "title": "Units", "type": "number" }, "usage": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "description": "Successful image token usage reported by fal/MiniMax.", "title": "Usage" } }, "required": [ "images", "units" ], "title": "H3ImageOutput", "type": "object" } ``` ## Example inputs and outputs Use the following example inputs and outputs to understand the model. ### Input example ```json { "prompt": "", "width": null, "height": null, "images": [ ], "n": 1, "output_format": "png" } ``` ### Output example ```json { } ``` ## Model code examples ### JavaScript ```javascript import { sunra } from "@sunra/client"; const result = await sunra.subscribe("minimax/minimax-h3-image-highspeed/image-editing", { input: { prompt: '', n: 1, output_format: 'png', images: [], width: null, height: null }, logs: true, onQueueUpdate: (update) => { console.log(`Status Update: ${update.status}, Request ID: ${update.request_id}`); }, }); console.log(result.data); console.log(result.requestId); ``` ### Python ```python import sunra_client result = sunra_client.subscribe( "minimax/minimax-h3-image-highspeed/image-editing", arguments={ "prompt": "", "n": 1, "output_format": "png", "images": [], "width": None, "height": None }, with_logs=True, on_enqueue=print, on_queue_update=print, ) print(result) ``` ### Java ```java import ai.sunra.client.*; import java.util.Map; import com.google.gson.JsonObject; var client = SunraClient.withEnvCredentials(); var response = client.subscribe( "minimax/minimax-h3-image-highspeed/image-editing", SubscribeOptions.builder() .input(Map.of( "prompt", "", "n", 1, "output_format", "png", "images", , "width", null, "height", null)) .resultType(JsonObject.class) .onQueueUpdate(update -> System.out.printf( "\nStatus Update: %s, Request ID: %s%n", update.getStatus(), update.getRequestId() )) .logs(true) .build() ); System.out.println("Completed!"); System.out.println(response.getData()); ``` ### Kotlin ```kotlin import ai.sunra.client.kt.* import com.google.gson.JsonObject val client = createSunraClient() val response = client.subscribe( endpointId = "minimax/minimax-h3-image-highspeed/image-editing", input = mapOf( "prompt" to "", "n" to 1, "output_format" to "png", "images" to , "width" to null, "height" to null), options = ai.sunra.client.kt.SubscribeOptions(logs = true), onUpdate = { update -> println("\nStatus Update: ${update.status}, Request ID: ${update.requestId}") } ) println("Completed!") println(response.data) ``` ### Curl ```bash curl --request POST \ --url https://api.sunra.ai/v1/queue/minimax/minimax-h3-image-highspeed/image-editing \ --header "Authorization: Key $SUNRA_KEY" \ --header "Content-Type: application/json" \ --data '{"prompt":"","n":1,"output_format":"png","images":[],"width":null,"height":null}' ``` ## Model readme > MiniMax H3 Image Highspeed supports text-to-image and multi-image editing. Prompts accept up to 32,000 characters; editing requires 1–16 input images. Each request can return 1–10 images in JPEG, PNG, WebP, or JPG format. > > Custom output sizes must contain 655,360–20,000,000 pixels with an aspect ratio from 1:3 to 3:1. Highspeed has a higher output-token rate than the standard tier. Billing follows Fal's successful-request token usage exactly; the $8 authorization hold is not a price cap.