## Basic model info - Model name: tripo/tripo tripo-h3.1 - Model description: Tripo H3.1 is a high-detail flagship model that generates PBR-ready 3D assets with up to 2 million faces from text, images, or multiple views. - Endpoint name: image-to-3d ## Model schema The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/tripo/tripo-h3.1/latest.json) ### Model input schema The model input schema is: ```json { "properties": { "auto_size": { "default": false, "description": "Auto-scale the model to real-world dimensions (meters).", "title": "Auto Size", "type": "boolean", "x-sr-order": 503 }, "face_limit": { "anyOf": [ { "maximum": 2000000, "minimum": 1000, "type": "integer" }, { "type": "null" } ], "description": "Target number of faces for the generated mesh. If not set, the model adaptively determines the count.", "title": "Face Limit", "x-sr-order": 405 }, "geometry_quality": { "default": "standard", "description": "Quality level for geometry.", "enum": [ "standard", "detailed" ], "title": "Geometry Quality", "type": "string", "x-sr-order": 402 }, "image": { "anyOf": [ { "format": "uri", "maxLength": 2083, "minLength": 1, "type": "string" }, { "type": "string" } ], "description": "URL of the input image for 3D model creation.", "title": "Image", "x-sr-order": 301 }, "model_seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "Seed for geometry generation reproducibility.", "title": "Model Seed", "x-sr-order": 403 }, "orientation": { "default": "default", "description": "Model orientation. 'align_image' auto-rotates to match the input image.", "enum": [ "default", "align_image" ], "title": "Orientation", "type": "string", "x-sr-order": 401 }, "pbr": { "default": true, "description": "Whether to generate PBR (Physically Based Rendering) materials. If true, texture is also enabled.", "title": "Pbr", "type": "boolean", "x-sr-order": 501 }, "quad": { "default": false, "description": "Generate quad (4-sided) mesh topology instead of triangles. When Tripo emits FBX bytes for quad output, the returned model file is FBX.", "title": "Quad", "type": "boolean", "x-sr-order": 504 }, "texture": { "default": true, "description": "Whether to generate textures for the model.", "title": "Texture", "type": "boolean", "x-sr-order": 502 }, "texture_alignment": { "default": "original_image", "description": "How textures are aligned. 'original_image' aligns to input image, 'geometry' aligns to generated geometry.", "enum": [ "original_image", "geometry" ], "title": "Texture Alignment", "type": "string", "x-sr-order": 404 }, "texture_quality": { "default": "standard", "description": "Quality level for textures. 'detailed' produces higher-resolution textures.", "enum": [ "standard", "detailed" ], "title": "Texture Quality", "type": "string", "x-sr-order": 407 }, "texture_seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "Seed for texture generation reproducibility.", "title": "Texture Seed", "x-sr-order": 406 } }, "required": [ "image" ], "title": "ImageTo3DInput", "type": "object" } ``` ### Model output schema The model output schema is: ```json { "properties": { "base_model": { "anyOf": [ { "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" }, { "type": "null" } ], "description": "Generated base 3D model mesh file" }, "model_mesh": { "anyOf": [ { "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" }, { "type": "null" } ], "description": "Generated 3D model mesh file" }, "pbr_model": { "anyOf": [ { "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" }, { "type": "null" } ], "description": "Generated PBR 3D model mesh file" }, "rendered_image": { "anyOf": [ { "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" }, { "type": "null" } ], "description": "A preview image of the model" }, "score": { "description": "Request cost in USD", "exclusiveMinimum": 0, "title": "Score", "type": "number" } }, "required": [ "score" ], "title": "TripoH31Output", "type": "object" } ``` ## Example inputs and outputs Use the following example inputs and outputs to understand the model. ### Input example ```json { "auto_size": false, "face_limit": null, "geometry_quality": "standard", "image": "", "model_seed": null, "orientation": "default", "pbr": true, "quad": false, "texture": true, "texture_alignment": "original_image", "texture_quality": "standard", "texture_seed": null } ``` ### Output example ```json { } ``` ## Model code examples ### JavaScript ```javascript import { sunra } from "@sunra/client"; const result = await sunra.subscribe("tripo/tripo-h3.1/image-to-3d", { input: { image: '', orientation: 'default', geometry_quality: 'standard', model_seed: null, texture_alignment: 'original_image', face_limit: null, texture_seed: null, texture_quality: 'standard', pbr: true, texture: true, auto_size: false, quad: false }, 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( "tripo/tripo-h3.1/image-to-3d", arguments={ "image": "", "orientation": "default", "geometry_quality": "standard", "model_seed": None, "texture_alignment": "original_image", "face_limit": None, "texture_seed": None, "texture_quality": "standard", "pbr": True, "texture": True, "auto_size": False, "quad": False }, 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( "tripo/tripo-h3.1/image-to-3d", SubscribeOptions.builder() .input(Map.of( "image", "", "orientation", "default", "geometry_quality", "standard", "model_seed", null, "texture_alignment", "original_image", "face_limit", null, "texture_seed", null, "texture_quality", "standard", "pbr", true, "texture", true, "auto_size", false, "quad", false)) .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 = "tripo/tripo-h3.1/image-to-3d", input = mapOf( "image" to "", "orientation" to "default", "geometry_quality" to "standard", "model_seed" to null, "texture_alignment" to "original_image", "face_limit" to null, "texture_seed" to null, "texture_quality" to "standard", "pbr" to true, "texture" to true, "auto_size" to false, "quad" to false), 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/tripo/tripo-h3.1/image-to-3d \ --header "Authorization: Key $SUNRA_KEY" \ --header "Content-Type: application/json" \ --data '{"image":"","orientation":"default","geometry_quality":"standard","model_seed":null,"texture_alignment":"original_image","face_limit":null,"texture_seed":null,"texture_quality":"standard","pbr":true,"texture":true,"auto_size":false,"quad":false}' ``` ## Model readme > Text, one image, or 2–4 views ordered [front, left, back, right]. Set texture=false for geometry-only output. Standard/detailed geometry and texture quality are independent; face_limit supports 1,000–2,000,000 faces. > > model_mesh contains the generated asset; base_model, pbr_model, and rendered_image are returned when available. Default triangle output is GLB; quad topology can return FBX. This model does not provide rigging or animation. > > Submit with POST https://api.sunra.ai/v1/queue/tripo/tripo-h3.1/ and Authorization: Key . Poll GET /v1/queue/requests/{request_id}/status, then fetch GET /v1/queue/requests/{request_id}. Generation is asynchronous and can take several minutes; do not resubmit a pending request. Failed requests expose an error; correct invalid inputs before retrying. > > Every returned file has a download URL, content type, name, and size. Download and retain assets needed for long-term use; the API does not promise a permanent URL lifetime. score is the request's USD billing quantity; the settled billing block reports the actual charge. See the endpoint price ladder for generation options and add-ons.