Tripo3d P2 Text To 3d API Documentation

Playground

Tripo3D P2 Text-to-3D turns a text description into a 3D model with Tripo’s P2 model with native quad topology (up to 50,000 triangles or 25,000 quads) for games and real-time pipelines. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Tripo3D P2 Text-to-3D generates a 3D model from a text description, with optional textures and PBR materials. Adjust the face count and choose triangle or quad output.

Why Choose This?

Geometry and materials — Generate geometry alone or include textures and PBR materials.
Texture choices — Choose standard, detailed, extreme, or fast texturing.
Mesh options — Adjust the face count and choose triangle or quad output.

Parameters

Parameter	Required	Description
prompt	Yes	Description of the 3D object: shape, material, style and scale. Up to 1024 characters.
negative_prompt	No	What the model should avoid. Up to 255 characters.
texture	No	Generate texture maps. Turn off (with pbr) for an untextured model at a lower price. Default: `true`.
pbr	No	Generate PBR materials (base color, metallic, roughness, normal). Turning it on also turns on texture. Default: `true`.
texture_quality	No	Texture quality: standard, detailed, extreme (8k), or fast (same texture size as standard). Options: `standard`, `detailed`, `extreme`, `fast`. Default: `standard`.
texture_version	No	Texture version. `fast` quality uses `v3.5-20260815`. Options: `v3.0-20250812`, `v3.5-20260815`. Default: `v3.0-20250812`.
delight	No	Remove the lighting baked into the source before texturing (texture model v3.5-20260815 only). Default: `true`.
quad	No	Output a native quad mesh (FBX). Default: `false`.
face_limit	No	Maximum number of faces: 48 to 50,000 triangles, or 48 to 25,000 quads. Omit for adaptive; 150+ for simple objects, 250+ for complex ones.
auto_size	No	Scale the model to real-world size in meters. Needs a textured model. Default: `false`.
export_uv	No	Unwrap UVs during generation. Default: `true`.
model_seed	No	Optional seed for geometry generation.
texture_seed	No	Optional seed for texture generation.

How to Use

Describe the object’s shape, materials, and style.
Choose geometry and texture settings.
Adjust optional mesh settings.
Submit the request and download the generated model.

Pricing

Configuration	Price per request
Geometry only	$1.20
With standard or fast textures	$1.32
With detailed textures	$1.44
With extreme (8k) textures	$1.56

Quad output does not add a separate charge.

For geometry-only output, turn off both texture and pbr. Enabling pbr also enables textures.

Notes

Turn off both texture and pbr for an untextured model.
fast uses the same texture size and price as standard and selects texture version v3.5-20260815.
delight affects texturing only with texture version v3.5-20260815; older texture versions ignore it.
Texture quality settings do not add a charge when textures are not generated.
auto_size estimates real-world scale and requires textured output.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "texture": true,
  "pbr": true,
  "texture_quality": "standard",
  "texture_version": "v3.0-20250812",
  "delight": true,
  "quad": false,
  "auto_size": false,
  "export_uv": true
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/tripo3d/p2/text-to-3d" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Retry temporary errors only while polling, never the submit request. Errors, retries and timeouts

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
prompt	string	Yes		0 ~ 1024 characters	Description of the 3D object: shape, material, style and scale. Up to 1024 characters.
negative_prompt	string	No		0 ~ 255 characters	What the model should avoid. Up to 255 characters.
image_seed	integer	No	-	-	Advanced option. Seed for the text-to-image step.
texture	boolean	No	true	-	Generate texture maps. Turn off (with pbr) for an untextured model at a lower price.
pbr	boolean	No	true	-	Generate PBR materials (base color, metallic, roughness, normal). Turning it on also turns on texture.
texture_quality	string	No	standard	standard, detailed, extreme, fast	Texture quality: standard, detailed (high resolution), extreme (8K) or fast (same size as standard, quicker; uses texture model v3.5-20260815).
texture_version	string	No	v3.0-20250812	v3.0-20250812, v3.5-20260815	Texture model. v3.5-20260815 is the newest; the fast quality and delight use it.
delight	boolean	No	true	-	Remove the lighting baked into the source before texturing (texture model v3.5-20260815 only).
quad	boolean	No	false	-	Output a native quad mesh (FBX).
face_limit	integer	No	-	48 ~ 50000	Maximum number of faces: 48 to 50,000 triangles, or 48 to 25,000 quads. Omit for adaptive; 150+ for simple objects, 250+ for complex ones.
auto_size	boolean	No	false	-	Scale the model to real-world size in meters. Needs a textured model.
export_uv	boolean	No	true	-	Unwrap UVs during generation. Turn off for faster generation and a smaller file.
model_seed	integer	No	-	-	Seed for the geometry: the same seed and input give the same mesh.
texture_seed	integer	No	-	-	Seed for the texture: keep model_seed and change texture_seed for new textures on the same mesh.

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.status	string	Task status. `completed` is successful; `failed`, `cancelled`, `timeout`, and `deleted` are failure terminal statuses.
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction
data.model	string	Model ID used for the prediction
data.outputs	array<string \| object>	Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urls	object	Object containing related API endpoints
data.status	string	Status: `completed` is successful; `failed`, `cancelled`, `timeout`, and `deleted` are failure terminal statuses
data.created_at	string	ISO timestamp of when the request was created
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Overview