Rodin 2.5 Fast Text to 3D

POST/v1/run

Rodin Gen-2.5 by Hyper3D (Deemos) generates game- and production-ready 3D assets from a text prompt, tuned for speed with the low tiers.

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 hyper3d/rodin/2.5/fast/text-to-3d.

Default: hyper3d/rodin/2.5/fast/text-to-3d

stringpromptrequired

A textual prompt to guide model generation. Required for Text-to-3D mode.

Optional<integer>seed

Seed (0–65535).

Range: 0 to 65535

Optional<string>geometry_file_format

Output file format.

Allowed values: glb, usdz, fbx, obj, stl

Default: glb

Optional<string>material

PBR, Shaded, All (both) or None.

Allowed values: PBR, Shaded, All, None

Default: Shaded

Optional<boolean>hd_texture

Enhanced texture post-processing.

Default: false

Optional<string>tier

Generation tier (quality / speed).

Allowed values: Gen-2.5-Minimum, Gen-2.5-Extreme-Low, Gen-2.5-Low

Default: Gen-2.5-Extreme-Low

Optional<string>quality_mesh_option

Combined quality and mesh type selection. Quad = smooth surfaces, Triangle = detailed geometry. Maps to `mesh_mode` (Quad/Raw) and `quality_override` (face count) on the Hyper3D API. Valid face counts depend on the selected tier. Up to 1M Triangle is supported for tiers Minimum, Extreme-Low, Low. For fast endpoint, this limit is up to 20K, primarily for prototyping and testing. For generating higher quality meshes, use the standard endpoint. Auto option will choose the advised options for each tier: 1. Gen-2.5-Minimum: 20K Triangle 2. Gen-2.5-Extreme-Low: 20K Triangle 3. Gen-2.5-Low: 20K Triangle

Allowed values: Auto, 1K Quad, 4K Quad, 8K Quad, 18K Quad, 20K Quad, 2K Triangle, 4K Triangle, 8K Triangle, 10K Triangle, 20K Triangle

Default: Auto

Optional<boolean>TAPose

Generate characters in T-pose or A-pose for rigging.

Default: false

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

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

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: text-to-3d

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "hyper3d/rodin/2.5/fast/text-to-3d",
  "prompt": "A futuristic robot with sleek metallic design."
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/f3d2e8a1-7c4b-4a12-9d2e-123456789abc \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "f3d2e8a1-7c4b-4a12-9d2e-123456789abc",
  "model": "hyper3d/rodin/2.5/fast/text-to-3d",
  "status": "running"
}