how much does Tripo 3.1 cost?

$0.01/credit, $0.10-$0.50/run (text: 10-40 credits, image/multiview: 20-50 credits). you pay per run from your inference shell credits. no subscription is required.

how do I run Tripo 3.1 via api?

call tripo/tripo-3-1 with the javascript or python sdk, the rest api, or `belt app run tripo/tripo-3-1` from a terminal. the api reference on this page lists every input.

Tripo 3.1 is made by tripo and runs on inference shell. every tripo app is listed at https://inference.sh/apps/tripo.

can my agent use Tripo 3.1?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

what are the alternatives to Tripo 3.1?

other 3d apps on inference shell include Tripo Auto Rig, Hunyuan 3D Auto Rigging, Hunyuan 3D 3.1, Rodin Gen-2.5. they run through the same api, so switching is a one-line change.

Tripo 3.1

Tripo 3.1 3D model generation from a text prompt, an image, or up to four views. PBR textures up to 8K, Ultra geometry, quad and smart low-poly topology, part segmentation.

text to 3d image to 3d

run in browser →run via API run with your agent

maker: tripo
category: 3d
input → output: text → 3d, image → 3d
runs via: api, javascript and python sdk, belt cli, mcp
updated: 2026-10-28
price: $0.01/credit, $0.10-$0.50/run (text: 10-40 credits, image/multiview: 20-50 credits)

api reference

about

tripo 3.1 3d model generation from a text prompt, an image, or up to four views. pbr textures up to 8k, ultra geometry, quad and smart low-poly topology, part segmentation.

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": "tripo/tripo-3-1",9    "input": {10      "prompt": "a stylized ceramic teapot shaped like a snail"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": "tripo/tripo-3-1",8    "input": {9      "prompt": "a stylized ceramic teapot shaped like a snail"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 $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{6    "app": "tripo/tripo-3-1",7    "input": {8      "prompt": "a stylized ceramic teapot shaped like a snail"9    }10  }' | jq -r '.data.id')1112# later: read its state. done when status is 10 (completed), 11 (failed) or 12 (cancelled)13curl -s https://api.inference.sh/tasks/$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": "tripo/tripo-3-1",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": "tripo/tripo-3-1",6    "input": {7        "prompt": "a stylized ceramic teapot shaped like a snail"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. used when no image is given.

example: "a stylized ceramic teapot shaped like a snail"maxLength:1024

negative_promptstring

what to keep out, for text to 3d.

maxLength:255

imagestring(file)

the object, or its front view when side views are given. jpeg or png.

left_imagestring(file)

left view of the object, for multiview. needs image.

back_imagestring(file)

back view of the object, for multiview. needs image.

right_imagestring(file)

right view of the object, for multiview. needs image.

textureboolean

texture the model. off returns the bare mesh and costs less.

default: true

pbrboolean

add pbr material maps. turns texture on.

default: true

texture_qualitystring

fast and standard cost the same; detailed (hd) and extreme (8k) cost more.

default: "standard"

options:"fast""standard""detailed""extreme"

geometry_qualitystring

detailed is ultra geometry and costs 20 credits more.

default: "standard"

options:"standard""detailed"

face_limitinteger

maximum face count. empty: chosen by tripo. up to 1.5m, 2m with detailed geometry, 150k with quad, 20k with smart_low_poly.

min:500max:2000000

quadboolean

quad mesh, delivered as fbx. costs 5 credits more.

default: false

smart_low_polyboolean

hand-crafted style low-poly topology. costs 10 credits more.

default: false

generate_partsboolean

split the model into editable parts. needs texture and pbr off; costs 20 credits more.

default: false

auto_sizeboolean

scale the model to real-world size in meters.

default: false

enable_image_autofixboolean

let tripo clean up a single input image first.

default: false

texture_alignmentstring

align the texture to the input image, or to the geometry.

default: "original_image"

options:"original_image""geometry"

orientationstring

align_image turns the model to match the image.

default: "default"

options:"default""align_image"

model_seedinteger

seed for the geometry.

min:0

texture_seedinteger

seed for the texture.

min:0

image_seedinteger

seed for the image tripo draws from the prompt, for text to 3d.

min:0

output

modelstring(file)*

the 3d model: glb, or fbx for a quad mesh.

rendered_imagestring(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

Rodin Gen-2.5

hyper3d/rodin-gen-2-5

$0.58/credit; Extreme-High tier +0.5 credits, texture extreme-high +2 credits

Meshy 7.1

meshy/meshy-7-1

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

more from tripo

Tripo Auto Rig

tripo/tripo-rig

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

new models

ready to run Tripo 3.1?

try in browser browse 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.

products

capabilities

get started

learn

build

community

from the blog

Tripo 3.1

api reference

about

get an api key

1. calling the api

install the client

run and get result

stream live updates

run in the background

2. authentication

3. files

automatic upload

manual upload

4. webhooks

5. schema

input

output

other 3d apps

more from tripo

new models

ready to run Tripo 3.1?