Meshy V7 Retexture API Documentation

Meshy V7 Retexture API Documentation

Playground

Try it on WaveSpeedAI!

Meshy 7 Retexture re-textures an existing 3D model from a text prompt or a reference image. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Meshy 7 Retexture generates new textures for an existing 3D model from a text description or reference image. Explore different materials, colors, and surface details.


Why Choose This?

  • Texture variations — Explore new materials and colors for an existing model.
  • Text or image guidance — Describe a style or supply a reference image.
  • Material options — Request PBR maps and choose whether to reuse the model’s UV layout.

Parameters

ParameterRequiredDescription
modelYesThe 3D model to process (GLB, GLTF, FBX, OBJ or STL).
promptNoDescribe the texture style. Provide a prompt or a texture_image.
texture_imageNoReference image for the texture style. Used when no prompt is given.
enable_pbrNoGenerate PBR maps. Default: false.
enable_original_uvNoReuse the model’s existing UV layout. Default: true.
texture_resolutionNoTexture resolution: 2k, 4k or 8k. Options: 2k, 4k, 8k. Default: 2k.

How to Use

  1. Upload the 3D model you want to retexture.
  2. Describe the desired materials and colors, or provide a texture reference image.
  3. Adjust the material options.
  4. Submit the request and download the textured model.

Pricing

Texture resolutionPrice per model
2k or 4k$0.40
8k$0.60

The prompt, reference image, PBR setting, and UV setting do not add separate charges.


Notes

  • Provide a prompt or texture_image. To use the reference image, leave prompt empty.
  • Use enable_original_uv=true to reuse a suitable existing UV layout. Set it to false to generate a new layout.
  • A reference image with a substantially different object shape may be harder to match to the model.

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'
{
  "model": "example",
  "enable_pbr": false,
  "enable_original_uv": true,
  "texture_resolution": "2k"
}
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/v7/retexture" \
  -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
modelstringYes--The 3D model to process (GLB, GLTF, FBX, OBJ or STL).
promptstringNo0 ~ 600 charactersDescribe the texture style. Provide a prompt or a texture_image.
texture_imagestringNo--Reference image for the texture style. Used when no prompt is given.
enable_pbrbooleanNofalse-Generate PBR maps.
enable_original_uvbooleanNotrue-Keep the model's own UVs.
texture_resolutionstringNo2k2k, 4k, 8kTexture resolution: 2k, 4k or 8k (8k costs more).

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.