Skip to content

Hunyuan3D

POST/v1/run

Hunyuan 3d V2 Mini Turbo by Tencent - convert 2D images into 3D models with AI. Generate textured 3D assets from single photos for games, AR/VR, e-commerce, and digital content creation.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to tencent/hunyuan-3d/v2/mini-turbo.

Default: tencent/hunyuan-3d/v2/mini-turbo

stringimagerequired

URL of image to use while generating the 3D model.

Optional<number>guidance_scale

Guidance scale for the model.

Range: 0 to 20

Default: 7.5

Optional<integer>num_inference_steps

Number of inference steps to perform.

Range: 1 to 50

Default: 50

Optional<integer>octree_resolution

Octree resolution for the model.

Range: 1 to 1024

Default: 256

Optional<boolean>textured_mesh

If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh.

Default: false

Optional<integer>seed

The same seed and the same prompt given to the same version of the model will output the same image every time.

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-3d

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async