Hyper3D Rodin v2.5 Text to 3D API

Hyper3D Rodin V2.5 Text-to-3D

Hyper3D Rodin V2.5 Text-to-3D generates 3D assets from natural-language prompts with flexible controls for mesh density, texture output, geometry behavior, symmetry, pose, and export format. It is suitable for product concepts, game assets, stylized objects, character prototyping, and other text-to-3D workflows where you want direct control over geometry and material output.

Why Choose This?

Prompt-based 3D generation
Turn a text description into a 3D asset with minimal setup.
Flexible mesh and quality options
Choose between quad and triangle outputs across multiple density levels.
Material and texture control
Generate PBR, shaded, full material sets, or geometry-only output depending on your workflow.
Geometry behavior settings
Use geometry_instruct_mode, symmetry options, and micro-detail settings to shape how the asset is built.
Multiple export formats
Export as glb, usdz, fbx, obj, or stl.
Production-ready workflow
Useful for concept art, product prototyping, game asset generation, and 3D content pipelines.

Parameters

Parameter	Required	Description
prompt	Yes	A text prompt describing the 3D asset to generate.
tier	No	Generation tier. Supported values: `Gen-2.5-Extreme-Low`, `Gen-2.5-Low`, `Gen-2.5-Medium`, `Gen-2.5-High`, `Gen-2.5-Extreme-High`. Default: `Gen-2.5-Medium`.
geometry_file_format	No	Output geometry file format. Supported values: `glb`, `usdz`, `fbx`, `obj`, `stl`. Default: `glb`.
material	No	Material output type. Supported values: `PBR`, `Shaded`, `All`, `None`. Default: `All`.
quality_and_mesh	No	Combined quality and mesh type selection. Supported values: `4K Quad`, `8K Quad`, `18K Quad`, `50K Quad`, `2K Triangle`, `20K Triangle`, `150K Triangle`, `500K Triangle`. Default: `18K Quad`.
texture_mode	No	Texture generation quality. Supported values: `legacy`, `extreme-low`, `low`, `medium`, `high`. Leave empty to let the provider choose.
geometry_instruct_mode	No	Geometry instruction mode. Supported values: `faithful`, `creative`. Default: `faithful`.
hd_texture	No	Enable enhanced texture post-processing. Default: `false`.
texture_delight	No	Remove baked lighting and highlights from generated textures. Default: `false`.
is_symmetric	No	Symmetry mode for the generated mesh. Supported values: `symmetric`, `balanced`, `asymmetric`, `unknown`. Default: `unknown`.
is_micro	No	Generate finer micro-scale geometric detail. Only effective with `Gen-2.5-Extreme-High`. Default: `false`.
ta_pose	No	Generate characters in T-pose or A-pose format. Default: `false`.
addons	No	Optional add-on. Supported value: `HighPack`. Enables 4K textures and higher-poly geometry.

How to Use

Write your prompt — describe the object, character, prop, or scene element you want to generate.
Choose a tier — use the default tier for general work, or select Gen-2.5-Extreme-High when you need the highest-quality generation.
Choose mesh and format settings — set quality_and_mesh, geometry_file_format, and material based on your downstream use.
Adjust geometry and texture controls (optional) — fine-tune texture_mode, geometry_instruct_mode, is_symmetric, hd_texture, and related settings.
Add HighPack (optional) — enable addons = HighPack if you need higher-end texture and geometry output.
Submit — run the model and download the generated 3D asset.

Example Prompt

A premium sci-fi helmet with matte black shell, subtle red light accents, clean hard-surface paneling, realistic materials, game-ready design

Pricing

Pricing is charged per generation.

Configuration	Cost
Standard tier	$0.40
Gen-2.5-Extreme-High	$0.80
Standard tier + HighPack	$1.20
Gen-2.5-Extreme-High + HighPack	$1.60

Billing Rules

Base price is $0.40 per generation
Gen-2.5-Extreme-High costs 2× the base price
HighPack adds an additional $0.80 per generation
HighPack and Gen-2.5-Extreme-High stack together
Other parameters do not affect pricing

Best Use Cases

Game asset prototyping — Generate early 3D assets for weapons, props, characters, and environment objects.
Product concept modeling — Explore 3D product forms from text descriptions.
Character base generation — Create initial meshes for stylized or realistic character workflows.
AR/VR content preparation — Build assets for immersive applications and previews.
Creative 3D ideation — Rapidly test multiple directions before manual refinement.

Pro Tips

Keep prompts visually specific about shape, material, and intended style.
Use faithful geometry mode when prompt accuracy matters more than creative interpretation.
Use creative when you want the model to take more design liberties.
Choose quad output when downstream retopology or sculpting workflows matter.
Use texture_delight if you want cleaner textures with less baked lighting.
Only enable is_micro when using Gen-2.5-Extreme-High, since it has no effect otherwise.
Add HighPack only when you need the extra texture and geometry quality, since it increases cost significantly.

Notes

prompt is required.
Gen-2.5-Extreme-High doubles the base generation cost.
HighPack adds an extra fixed charge on top of the selected tier.
is_micro is only effective with Gen-2.5-Extreme-High.
geometry_file_format defaults to glb.
material defaults to All.
quality_and_mesh defaults to 18K Quad.

Related Models

Other Hyper3D Rodin workflows — Useful when you need image-to-3D or different 3D generation paths.
3D asset generation pipelines — Useful when text-to-3D is only one part of a broader modeling workflow.
High-detail asset workflows — Useful when downstream rendering, real-time engines, or modeling tools need more specific export formats or mesh structures.

Rodin v2.5 Text To 3d API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/hyper3d/rodin-v2.5/text-to-3d with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Rodin v2.5 Text To 3d below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/hyper3d/rodin-v2.5/text-to-3d" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "tier": "Gen-2.5-Medium",
    "geometry_file_format": "glb",
    "material": "All",
    "quality_and_mesh": "18K Quad",
    "texture_mode": "legacy",
    "geometry_instruct_mode": "faithful",
    "hd_texture": false,
    "texture_delight": false,
    "is_symmetric": "unknown",
    "is_micro": false,
    "ta_pose": false,
    "addons": "HighPack"
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("hyper3d/rodin-v2.5/text-to-3d", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "tier": "Gen-2.5-Medium",
        "geometry_file_format": "glb",
        "material": "All",
        "quality_and_mesh": "18K Quad",
        "texture_mode": "legacy",
        "geometry_instruct_mode": "faithful",
        "hd_texture": false,
        "texture_delight": false,
        "is_symmetric": "unknown",
        "is_micro": false,
        "ta_pose": false,
        "addons": "HighPack"
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "hyper3d/rodin-v2.5/text-to-3d",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "tier": "Gen-2.5-Medium",
    "geometry_file_format": "glb",
    "material": "All",
    "quality_and_mesh": "18K Quad",
    "texture_mode": "legacy",
    "geometry_instruct_mode": "faithful",
    "hd_texture": false,
    "texture_delight": false,
    "is_symmetric": "unknown",
    "is_micro": false,
    "ta_pose": false,
    "addons": "HighPack"
}
)

print(output["outputs"][0])  # → URL of the generated output

Rodin v2.5 Text To 3d API — Frequently asked questions

What is the Rodin v2.5 Text To 3d API?

Rodin v2.5 Text To 3d is a Hyper3d model for 3D asset generation, exposed as a REST API on WaveSpeedAI. Hyper3D Rodin v2.5 Text to 3D is a fast AI 3D asset generation model that creates production-ready 3D assets from text prompts with clean meshes, UVs, and textures. Ready-to-use REST inference API for game assets, e-commerce 3D models, product visualization, AR/VR content, digital twins, creative design, and professional text-to-3D workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Rodin v2.5 Text To 3d API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/hyper3d/hyper3d-rodin-v2.5-text-to-3d.

How much does Rodin v2.5 Text To 3d cost per run?

Rodin v2.5 Text To 3d starts at $0.40 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Rodin v2.5 Text To 3d accept?

Key inputs: `prompt`, `addons`, `geometry_file_format`, `geometry_instruct_mode`, `hd_texture`, `is_micro`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/hyper3d/hyper3d-rodin-v2.5-text-to-3d.

How do I get started with the Rodin v2.5 Text To 3d API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Rodin v2.5 Text To 3d outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Hyper3d). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

サンプルすべて表示

関連モデル

README