Tripo3d P2 Text To 3d API Documentation

Tripo3d P2 Text To 3d API Documentation

Playground

Tripo P2 Text-to-3D generates detailed 3D meshes from text prompts, with optional PBR textures, selectable texture quality, and triangle or quad topology for game assets, product visualization, 3D design, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Tripo P2 Text-to-3D generates a downloadable 3D model directly from a text description, with optional textures and PBR materials. Describe the object you want to create, then control mesh topology, face count, texture quality, UVs, orientation, and real-world scaling for downstream 3D workflows.

It supports both triangle and quad meshes, multiple texture-quality tiers, and reproducible geometry and texture generation through dedicated seed controls.

Why Choose This?

• Text-to-3D generation
  Create complete 3D assets directly from natural-language descriptions.

• Triangle or quad topology
  Generate standard triangle meshes or enable quad for quad-based topology.

• Flexible texture quality
  Choose fast, standard, detailed, or extreme texture quality depending on speed, cost, and fidelity requirements.

• Optional PBR materials
  Generate PBR material maps for more realistic rendering and downstream asset workflows.

• Face-count control
  Set a target mesh complexity with face_limit, or omit it for adaptive face-count selection.

• UV export
  Generate UV coordinates for texturing and further editing in 3D software.

• Real-world scaling
  Enable auto_size to automatically scale the generated model to real-world dimensions in meters.

• Reproducible generation
  Use separate seeds for geometry, texture, and the internal text-to-image stage.

Parameters

How to Use

1. Describe the object — Write a clear prompt describing the shape, structure, materials, and important visual features.
2. Add exclusions optional — Use negative_prompt to specify unwanted characteristics.
3. Configure textures — Enable or disable texture and pbr, then choose the desired texture quality.
4. Configure geometry optional — Set face_limit and choose triangle or quad topology.
5. Configure export options optional — Adjust UV export, orientation, and real-world scaling when needed.
6. Set seeds optional — Use fixed geometry, texture, or image seeds when reproducibility matters.
7. Submit — Generate and download the completed 3D model.

Pricing

Pricing is based on whether textures are generated and the selected texture_quality.

The base geometry price is $1.20 per generated model.

When either texture or pbr is enabled:

• fast or standard adds $0.12
• detailed adds $0.24
• extreme adds $0.36

Both texture and pbr default to true, while texture_quality defaults to standard, so the default request costs $1.32.

Set both texture=false and pbr=false for the $1.20 untextured price.

quad, face_limit, seeds, delight, auto_size, export_uv, and export_orientation do not add separate charges.

Best Use Cases

• Game asset prototyping — Quickly create props, objects, environment assets, and concept meshes from text.
• Product visualization — Generate 3D concepts for products, furniture, devices, packaging, or industrial objects.
• 3D concept exploration — Turn early design ideas into editable 3D assets.
• Textured asset generation — Create models with textures and optional PBR materials for rendering workflows.
• Quad-mesh workflows — Generate quad topology when downstream editing or mesh workflows benefit from it.
• 3D content production — Create assets for further refinement in modeling, rendering, animation, or game-development tools.

Pro Tips

• Describe one primary object clearly instead of combining several unrelated objects in the same prompt.
• Include shape, materials, proportions, structural details, and visual style when they matter.
• Use standard texture quality for initial iterations and move to detailed or extreme when higher texture fidelity is needed.
• Disable both texture and pbr when you only need geometry and want the lowest-cost generation.
• Use quad=true when quad topology is important for downstream editing, and keep face_limit at or below 25000.
• Omit face_limit when you want the model to choose mesh complexity adaptively.
• Enable auto_size when real-world scale in meters matters.
• Use fixed seeds when comparing prompt, geometry, or texture changes.

Notes

• prompt is required and supports up to 1024 characters.
• negative_prompt supports up to 255 characters.
• face_limit supports 48–50000 faces for triangle meshes.
• Quad meshes support up to 25000 faces.
• fast texture quality requires texture_version=v3.5-20260815.
• Other supported texture versions include v3.0-20250812 and v2.5-20250123.
• texture and pbr both default to true.
• export_uv defaults to true.
• The API returns the primary model download URL.
• The output may be a GLB or FBX model; no output-format selector is exposed.
• Optional parameters should be omitted when unused rather than passed as null.

Related Models

• Tripo P2 Text-to-3D — Generate 3D models directly from text descriptions.
• Tripo P2 Image-to-3D — Generate 3D models from image references.

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": "v3.5-20260815",
  "quad": false,
  "delight": true,
  "auto_size": false,
  "export_uv": true,
  "export_orientation": "+x"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -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}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters