Inference Logoinference shell

Rodin Gen-2.5

Hyper3D Rodin Gen-2.5 by Deemos. 3D models from a text prompt or up to five images, five quality tiers, raw or quad meshes, PBR textures up to 8K, GLB, USDZ, FBX, OBJ or STL.

text to 3dimage to 3d
run in browser →run via APIrun with your agent
maker
hyper3d
category
3d
input → output
text → 3d, image → 3d
runs via
api, javascript and python sdk, belt cli, mcp
updated
2026-10-28
price
$0.58/credit; Extreme-High tier +0.5 credits, texture extreme-high +2 credits

api reference

about

hyper3d rodin gen-2.5 by deemos. 3d models from a text prompt or up to five images, five quality tiers, raw or quad meshes, pbr textures up to 8k, glb, usdz, fbx, obj or stl.

get an api key

create one in settings → api keys. the examples read it from INFERENCE_API_KEY.

bash
1export INFERENCE_API_KEY="inf_your_key"

1. calling the api

install the client

nothing to install. any http client works; the examples use curl, and jq to read responses. every response wraps its result in a data field.

run and get result

send "wait": true to hold the connection until the task finishes. without it the call returns right away with the task still running.

bash
12# "wait": true holds the connection until the task finishes.3# the response is {"data": {"id", "status", "status_text", "output", ...}}4curl -X POST https://api.inference.sh/apps/run \5  -H "Authorization: Bearer $INFERENCE_API_KEY" \6  -H "Content-Type: application/json" \7  -d '{8    "app": "hyper3d/rodin-gen-2-5",9    "input": {10      "prompt": "a carved wooden owl perched on a branch"11    },12    "wait": true13  }'

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks. send "stream": true and the response is a server-sent event stream that ends when the task does.

bash
12# "stream": true answers with server-sent events until the task finishes3curl -N -X POST https://api.inference.sh/apps/run \4  -H "Authorization: Bearer $INFERENCE_API_KEY" \5  -H "Content-Type: application/json" \6  -d '{7    "app": "hyper3d/rodin-gen-2-5",8    "input": {9      "prompt": "a carved wooden owl perched on a branch"10    },11    "stream": true12  }'

run in the background

start the task and get its id back right away, then check on it later. for long tasks, or when you'd rather be called back, see webhooks.

bash
1# without "wait" the call returns the task right away (status 1, "received")2TASK_ID=$(curl -s -X POST https://api.inference.sh/apps/run \3  -H "Authorization: Bearer $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{6    "app": "hyper3d/rodin-gen-2-5",7    "input": {8      "prompt": "a carved wooden owl perched on a branch"9    }10  }' | jq -r '.data.id')1112# later: read its state. done when status is 10 (completed), 11 (failed) or 12 (cancelled)13curl -s https://api.inference.sh/tasks/$TASK_ID \14  -H "Authorization: Bearer $INFERENCE_API_KEY" | jq '.data | {status, status_text, output}'

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

pass urls directly or use data uris for inline content.

bash
1# pass URLs or data URIs as input values2curl -X POST https://api.inference.sh/apps/run \3  -H "Authorization: Bearer $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{6    "app": "hyper3d/rodin-gen-2-5",7    "input": {8      "image": "https://example.com/image.png",9      "audio": "data:audio/mp3;base64,..."10    },11    "wait": true12  }'

manual upload

you can also upload files manually and use the returned url.

bash
1# 1. create the file: the response has an upload_url and the file's uri2FILE=$(curl -s -X POST https://api.inference.sh/files \3  -H "Authorization: Bearer $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{"files": [{"filename": "image.png", "content_type": "image/png"}]}')67# 2. PUT the bytes to upload_url8curl -X PUT "$(echo "$FILE" | jq -r '.data[0].upload_url')" \9  -H "Content-Type: image/png" \10  --data-binary @image.png1112# 3. pass the uri as an input value13echo "$FILE" | jq -r '.data[0].uri'

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

bash
1curl -X POST https://api.inference.sh/apps/run \2  -H "Authorization: Bearer $INFERENCE_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "app": "hyper3d/rodin-gen-2-5",6    "input": {7        "prompt": "a carved wooden owl perched on a branch"8    },9    "webhook": "https://your-server.com/webhook"10  }'

webhook payload

your endpoint receives a JSON POST with the task result:

json
1{2  "event": "task.completed",3  "timestamp": "2024-01-15T10:30:05Z",4  "data": {5    "id": "task_abc123",6    "short_id": "abc123",7    "status": 10,8    "status_text": "completed",9    "output": { ... },10    "created_at": "2024-01-15T10:30:00Z",11    "updated_at": "2024-01-15T10:30:05Z"12  }13}
eventstringtask.completed, task.failed or task.cancelled
timestampstringiso timestamp of the delivery
data.idstringtask id
data.short_idstringshort task id
data.statusnumberterminal status (10=completed, 11=failed, 12=cancelled, 13=rejected)
data.status_textstringthe status as a word: completed, failed or cancelled
data.outputobjecttask output (when completed)
data.errorstringerror message (when failed, omitted otherwise)
data.session_idstringsession id (when the task ran in a session, omitted otherwise)
data.created_atstringiso timestamp
data.updated_atstringiso timestamp

5. schema

input

promptstring

what to make, for text to 3d. with images, leave it empty unless the images need explaining.

example: "a carved wooden owl perched on a branch"maxLength:1024
imagesarray

one to five images of one object. the first image sets the materials.

tierstring

quality tier. extreme-high costs 0.5 credits more and adds a mesh of up to 10m faces.

default: "Gen-2.5-Medium"
options:"Gen-2.5-Extreme-Low""Gen-2.5-Low""Gen-2.5-Medium""Gen-2.5-High""Gen-2.5-Extreme-High"
mesh_modestring

raw triangles, or a quad mesh.

default: "Raw"
options:"Raw""Quad"
qualitystring

face count. raw: 1m, 500k, 60k, 20k. quad: 50k, 18k, 8k, 4k.

default: "medium"
options:"high""medium""low""extra-low"
quality_overrideinteger

exact face count, instead of quality. above 1m needs the high or extreme-high tier; quad takes at most 200k.

min:500max:2000000
geometry_file_formatstring

file format of the model.

default: "glb"
options:"glb""usdz""fbx""obj""stl"
materialstring

pbr maps, baked shading, both, hybrid, or no material.

default: "PBR"
options:"PBR""Shaded""All""Hybrid""None"
texture_modestring

texture quality. empty: follows the tier. extreme-high gives 6k textures and costs 2 credits more.

options:"legacy""extreme-low""low""medium""high""extreme-high"
hd_textureboolean

higher quality texture.

default: false
uhd_textureboolean

4k textures, 8k with high_pack.

default: false
high_packboolean

the highpack add-on: 4k textures, 8k with uhd_texture.

default: false
texture_delightboolean

remove lighting baked into the images from the texture.

default: false
geometry_instruct_modestring

faithful follows the images more literally (experimental).

default: "creative"
options:"creative""faithful"
is_symmetricstring

symmetry of the object, if known.

default: "unknown"
options:"unknown""symmetric""balanced""asymmetric"
is_microboolean

micro detail. extreme-high tier only.

default: false
t_a_poseboolean

put a human-like subject in a t or a pose.

default: false
use_original_alphaboolean

use the images' own transparency as the mask.

default: false
seedinteger

seed, 0 to 65535.

min:0max:65535

output

filesarray

every other file hyper3d returned: textures, and the high-poly mesh of extreme-high.

modelstring(file)*

the 3d model.

previewstring(file)

a preview render of the model.

other 3d apps

Tripo Auto Rig

tripo/tripo-rig

$0.01/credit (rig check free, auto rig 25 credits, retarget 10 credits/animation)

Hunyuan 3D Auto Rigging

tencent/hunyuan-3d-auto-rigging

$0.02/credit, 10 credits/call ($0.20/call)

Hunyuan 3D 3.1

tencent/hunyuan-3d-3-1

$0.02/credit; Geometry 15cr, Normal 25cr, +10cr views/PBR/face-count

Meshy 7.1

meshy/meshy-7-1

$0.0127/Meshy credit (20 base + 10-15 texture + 5 hi-res geo)

Tripo 3.1

tripo/tripo-3-1

$0.01/credit, $0.10-$0.50/run (text: 10-40 credits, image/multiview: 20-50 credits)

new models

  1. Tripo Auto Rig

    tripo/tripo-rig

    3d$0.01/credit (rig check free, auto rig 25 credits, retarget 10 credits/animation)

  2. Hunyuan 3D Auto Rigging

    tencent/hunyuan-3d-auto-rigging

    3d$0.02/credit, 10 credits/call ($0.20/call)

  3. Hunyuan 3D 3.1

    tencent/hunyuan-3d-3-1

    3d$0.02/credit; Geometry 15cr, Normal 25cr, +10cr views/PBR/face-count

  4. Meshy 7.1

    meshy/meshy-7-1

    3d$0.0127/Meshy credit (20 base + 10-15 texture + 5 hi-res geo)

  5. Tripo 3.1

    tripo/tripo-3-1

    3d$0.01/credit, $0.10-$0.50/run (text: 10-40 credits, image/multiview: 20-50 credits)

ready to run Rodin Gen-2.5?

try in browserbrowse all apps

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.