Meshy T2 Text To 3d API Documentation

Meshy T2 Text To 3d API Documentation

Playground

Try it on WaveSpeedAI!

Meshy T2 Text-to-3D converts text descriptions into lightweight low-poly 3D meshes for game assets, rapid prototyping, stylized 3D content, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Meshy T2 Text-to-3D turns a text description into a low-poly, triangle-mesh 3D model. Choose geometry-only or textured output, set a target triangle count, and optionally add rigging or an animation to a humanoid character.


Why Choose This?

  • Clean low-poly meshes — Native triangle topology with a target face count up to 15,000.
  • Flexible output — Generate geometry alone or add textures.
  • Texture options — Guide texturing with a description or reference image.
  • Optional character animation — Add rigging and one animation action to a suitable humanoid model.

Parameters

ParameterRequiredDescription
promptYesDescribe the object to generate. Up to 600 characters.
modeNopreview generates an untextured mesh; full also generates textures. Default: full.
negative_promptNoOptional negative prompt.
seedNoOptional seed value.
texture_promptNoOptional text description to guide the texture.
texture_imageNoOptional image to guide the texture. If both texture references are supplied, texture_prompt takes priority.
enable_pbrNoRequest metallic, roughness and normal maps when generating textures. Default: false.
texture_resolutionNoTexture size: 2k, 4k or 8k. Default: 2k.
target_polycountNoTarget triangle count: 100-15000. Default: 15000.
pose_modeNoOptional character pose: a-pose or t-pose.
auto_sizeNoEstimate the object’s real-world size and scale it accordingly. Default: false.
enable_riggingNoAdd a skeleton to a textured humanoid character. Default: false.
rigging_height_metersNoApproximate character height in meters for rigging. Default: 1.7.
enable_animationNoRig the character and apply one action selected by animation_action_id. Default: false.
animation_action_idNoAnimation action ID to apply when animation is enabled. Default: 92.

How to Use

  1. Describe the object you want to create.
  2. Choose geometry-only or textured output and set the target triangle count.
  3. For a humanoid character, optionally enable rigging or animation.
  4. Submit the request and download the generated 3D files.

Pricing

Generation optionPrice per request
Geometry only (mode=preview)$0.20
With 2k or 4k textures$0.60
With 8k textures$0.80
Optional additionExtra charge
Rigging$0.20
One animation action, excluding rigging$0.12

Enabling animation also includes rigging, for a total extra charge of $0.32. The total is the generation price plus the selected additions.


Notes

  • The mesh always uses triangle faces; the generated face count may differ from target_polycount.
  • Use either texture_prompt or texture_image to guide texturing. If both are provided, the text prompt takes priority.
  • Rigging and animation are intended for textured humanoid characters with clearly defined limbs. They are not suitable for untextured meshes or non-humanoid objects.

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",
  "mode": "full",
  "enable_pbr": false,
  "texture_resolution": "2k",
  "target_polycount": 15000,
  "pose_mode": "a-pose",
  "auto_size": false,
  "enable_rigging": false,
  "rigging_height_meters": 1.7,
  "enable_animation": false,
  "animation_action_id": 92
}
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/meshy/t2/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

ParameterTypeRequiredDefaultRangeDescription
promptstringYes0 ~ 600 charactersDescribe the object to generate. Up to 600 characters.
modestringNofullpreview, fullpreview makes an untextured mesh; full also textures it.
negative_promptstringNo-Optional negative prompt.
seedintegerNo--Optional seed value.
texture_promptstringNo--Optional description of the texture.
texture_imagestringNo--Optional reference image for the texture. If both texture_prompt and texture_image are provided, texture_prompt takes priority.
enable_pbrbooleanNofalse-Generate PBR maps (metallic, roughness, normal).
texture_resolutionstringNo2k2k, 4k, 8kTexture resolution: 2k, 4k or 8k (8k costs more).
target_polycountintegerNo15000100 ~ 15000Target number of polygons (triangles), 100-15000.
pose_modestringNo-a-pose, t-poseGenerate characters in an A-pose or T-pose (useful before rigging).
auto_sizebooleanNofalse-Estimate the real-world size of the object and scale the model to it.
enable_riggingbooleanNofalse-Rig the generated character (humanoids). The rigged model is returned after the model.
rigging_height_metersnumberNo1.7-Character height in meters used for rigging.
enable_animationbooleanNofalse-Rig and animate the character with animation_action_id. The animated model is returned last.
animation_action_idintegerNo92-Animation action ID to apply when animation is enabled.

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

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<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.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.