Meshy 7.1 Multi Image to 3D API

meshy/v7.1/multi-image-to-3d

Meshy 7.1 Multi Image to 3D rebuilds one object from 1–4 views into a textured 3D model with up to 2K geometry and PBR maps. Combining front, side and back views gives the mesh more information about hidden surfaces, while you keep control of topology, polygon count and rigging.

Input

Image UrlsRequired

Drag and drop files, paste from clipboard, or provide a URL. Add 1–4 images of the same object from different angles, such as front, side, back and three-quarter.

4/4 files added

Should TextureOptional

Geometry ResolutionOptional

TopologyOptional

Target PolycountOptional

Should RemeshOptional

Symmetry ModeOptional

Advanced settings

Enable PbrOptional

Texture PromptOptional

Texture Image UrlOptional

Pose ModeOptional

Enable RiggingOptional

Rigging Height MetersOptional

Enable AnimationOptional

Animation Action IdOptional

Enable Safety CheckerOptional

Output

Meshy 7.1 Multi Image to 3D model ready

Loading 3D preview…

Continue using

Meshy 7.1 Text to 3D Meshy 7.1 Image to 3D Meshy 6 Multi Image to 3D

Meshy 7.1 Multi Image to 3D API

Quick Start

Submit Meshy 7.1 Multi Image to 3D inputs, retain task_id, and query the task for the returned files.

Authenticate for Meshy 7.1 Multi Image to 3D

Send your Vidgo API key in the Bearer authorization header.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer YOUR_API_KEY

Submit a Meshy 7.1 Multi Image to 3D request

Place model at the request root and the image_urls value inside input.

Request example

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "meshy/v7.1/multi-image-to-3d",
  "input": {
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v1/01/input-1.png",
      "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v1/01/input-2.png",
      "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v1/01/input-3.png",
      "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v1/01/input-4.png"
    ],
    "geometry_resolution": "2k",
    "should_texture": true,
    "enable_pbr": true,
    "topology": "triangle",
    "target_polycount": 30000,
    "symmetry_mode": "auto"
  }
}
JSON
)

RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
  printf 'API error: %s
' "$RESPONSE" >&2
  exit 1
fi
printf '%s
' "$RESPONSE"

Check the Meshy 7.1 Multi Image to 3D task

Query the returned task_id until status is finished or failed.

Status endpoint

GET https://api.vidgo.ai/api/generate/status/{task_id}

When status is finished, inspect files and download the returned assets.

not_startedrunningfinishedfailed

Submission response

{
  "code": 200,
  "data": {
    "task_id": "VF7VZ7G81NVEN3II",
    "status": "not_started",
    "created_time": "2026-11-05T07:07:57"
  }
}

Completed response

{
  "code": 200,
  "data": {
    "task_id": "VF7VZ7G81NVEN3II",
    "status": "finished",
    "files": [
      {
        "file_url": "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v2/01/model-01.glb",
        "file_type": "3d",
        "label": "model_glb",
        "format": "glb",
        "file_name": "model-01.glb"
      },
      {
        "file_url": "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v2/01/model-01.fbx",
        "file_type": "3d",
        "label": "model_fbx",
        "format": "fbx",
        "file_name": "model-01.fbx"
      },
      {
        "file_url": "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v2/01/model-01.obj",
        "file_type": "3d",
        "label": "model_obj",
        "format": "obj",
        "file_name": "model-01.obj"
      },
      {
        "file_url": "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v2/01/model-01.stl",
        "file_type": "3d",
        "label": "model_stl",
        "format": "stl",
        "file_name": "model-01.stl"
      },
      {
        "file_url": "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v2/01/model-01.usdz",
        "file_type": "3d",
        "label": "model_usdz",
        "format": "usdz",
        "file_name": "model-01.usdz"
      },
      {
        "file_url": "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v2/01/thumbnail-01.png",
        "file_type": "image",
        "label": "thumbnail",
        "format": "png",
        "file_name": "thumbnail-01.png"
      }
    ],
    "created_time": "2026-11-05T07:07:57",
    "error_message": null,
    "progress": 100
  }
}

Read Meshy 7.1 Multi Image to 3D files

Read each returned files item for file_url, file_type, label, and format.

Read Meshy 7.1 Multi Image to 3D files

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "meshy/v7.1/multi-image-to-3d",
  "input": {
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v1/01/input-1.png",
      "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v1/01/input-2.png",
      "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v1/01/input-3.png",
      "https://cdn.vidgo.ai/apis/models/meshy/v7.1/multi-image-to-3d/v1/01/input-4.png"
    ],
    "geometry_resolution": "2k",
    "should_texture": true,
    "enable_pbr": true,
    "topology": "triangle",
    "target_polycount": 30000,
    "symmetry_mode": "auto"
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
  printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
  if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
    printf 'Timed out after 600 seconds
' >&2
    exit 1
  fi
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
  BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
  if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
    printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
    exit 1
  fi

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep "$POLL_DELAY"
      if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Input Parameters

Place model and optional callback_url at the request root; put the fields listed below inside input.

Field	Type	Required	Default	Description
model	string	Yes	—	meshy/v7.1/multi-image-to-3d
input	object	Yes	—	Generation settings for this endpoint.
input.image_urls	string[]	Yes	—	Add 1–4 images of the same object from different angles, such as front, side, back and three-quarter.
input.should_texture	boolean	No	true	true textures the model (+80 credits); false returns geometry only. Default true.
input.geometry_resolution	string	No	—	Geometry detail: standard, 2k. Available with model_type standard. Leave unset for the default.
input.topology	string	No	triangle	triangle or quad faces. Default triangle.
input.target_polycount	integer	No	30000	Target polygon count: 100–300,000 (default 30,000), or 100–15,000 (default 4,000) with smart-topology.
input.should_remesh	boolean	No	true	true remeshes to the chosen topology and polygon target; false keeps the raw triangle mesh. Default true.
input.symmetry_mode	string	No	auto	off, auto or on. Default auto.
input.enable_pbr	boolean	No	false	Adds metallic, roughness and normal maps to the base color. Requires should_texture true.
input.texture_prompt	string	No	—	Up to 600 characters describing colors, patterns and materials. Requires should_texture true.
input.texture_image_url	string	No	—	A public image URL used as a texture reference. Requires should_texture true.
input.pose_mode	string	No	""	a-pose or t-pose for characters, or empty for no pose. Default empty.
input.enable_rigging	boolean	No	false	Adds a humanoid skeleton (+40 credits). Default false.
input.rigging_height_meters	number	No	1.7	Character height in meters for rigging, greater than 0. Default 1.7.
input.enable_animation	boolean	No	false	Applies an animation preset (+24 credits). Requires enable_rigging true.
input.animation_action_id	integer	No	92	Animation preset ID from 0 to 696. Default 92.
input.enable_safety_checker	boolean	No	true	Runs the upstream safety checker. Default true.
callback_url	string	No	—	Provide a public HTTP(S) URL for completed or failed task notifications.

Response Fields

The status response reports task state, progress, and returned files.

Field	Type	Description
code	integer	API response code.
data.task_id	string	Task ID for status queries.
data.status	string	Task state: not_started, running, finished, or failed.
data.progress	integer	Reported generation progress from 0 to 100.
data.files	array	Generated model, preview image, and companion files.
data.files[].file_url	string	URL for a returned file.
data.files[].file_type	string	File category: 3d, image or other.
data.files[].label	string	File role, such as model_glb or thumbnail.
data.files[].format	string	File format, such as glb or png.
data.files[].file_name	string	File name when provided.
data.files[].file_size	integer	File size in bytes when provided.
data.error_message	string \| null	Error details for a failed task.

Task Lifecycle

Use task_id to check the same generation until it finishes or fails.

not_started
The task has been accepted and awaits generation.
running
The 3D model is being generated; continue querying this task.
finished
Generation is complete; read files for the assets.
failed
The task failed; read error_message before submitting another request.

Polling and Errors

Keep the task IDIf a status query is interrupted, use the same task_id to retrieve the latest state.
Download returned assetsUse file_url and file_name from each returned file to download the model and companion assets.
Review a failed generationWhen status is failed, read error_message, then review the input before submitting a new task.

Endpoint Specifications

Item	Value	Description
Input	1–4 images	Views of the same object from different angles.
Geometry resolution	standard, 2k	Set with geometry_resolution.
Topology	triangle, quad	Target polycount 100–300,000.
Output files	GLB, FBX, OBJ, USDZ, STL	Formats returned depend on the task; read files for the full list.
Price	$1.200 default	160 credits geometry + 80 texture; +40 rigging, +24 animation.

View the Meshy 7.1 Multi Image to 3D API docs

Meshy 7.1 Multi Image to 3D

Meshy 7.1 Multi Image to 3D is a Meshy model that reconstructs one object from up to four photos taken from different angles. Extra views give the 7.1 generation more evidence about the back and sides, which helps products, props and collectibles keep their real proportions. Geometry resolution goes up to 2k, and topology, polygon targets, PBR textures and rigging work as on the single-image endpoint.

Why choose Meshy 7.1 Multi Image to 3D?

More views, fewer guessesAdd up to four angles of the same object so the back and sides follow your photos.
Detail up to 2K geometryChoose standard or 2k geometry resolution for each reconstruction.
Geometry-only studiesTurn should_texture off for 160-credit shape checks before texturing.
Same mesh and rigging controlsTopology, polygon targets, symmetry, PBR maps and rigging work as on the single-image endpoint.

Parameters

Parameter	Requirement	What it controls
image_urls	Required	Add 1–4 images of the same object from different angles, such as front, side, back and three-quarter.
should_texture	Optional	true textures the model (+80 credits); false returns geometry only. Default true. Default`true`
geometry_resolution	Optional	Geometry detail: standard, 2k. Available with model_type standard. Leave unset for the default. `standard2k`
topology	Optional	triangle or quad faces. Default triangle. Default`trianglequad`
target_polycount	Optional	Target polygon count: 100–300,000 (default 30,000), or 100–15,000 (default 4,000) with smart-topology. Default`30000`
should_remesh	Optional	true remeshes to the chosen topology and polygon target; false keeps the raw triangle mesh. Default true. Default`true`
symmetry_mode	Optional	off, auto or on. Default auto. Default`autooffon`
enable_pbr	Optional	Adds metallic, roughness and normal maps to the base color. Requires should_texture true. Default`false`
texture_prompt	Optional	Up to 600 characters describing colors, patterns and materials. Requires should_texture true.
texture_image_url	Optional	A public image URL used as a texture reference. Requires should_texture true.
pose_mode	Optional	a-pose or t-pose for characters, or empty for no pose. Default empty. Default`""a-poset-pose`
enable_rigging	Optional	Adds a humanoid skeleton (+40 credits). Default false. Default`false`
rigging_height_meters	Optional	Character height in meters for rigging, greater than 0. Default 1.7. Default`1.7`
enable_animation	Optional	Applies an animation preset (+24 credits). Requires enable_rigging true. Default`false`
animation_action_id	Optional	Animation preset ID from 0 to 696. Default 92. Default`92`
enable_safety_checker	Optional	Runs the upstream safety checker. Default true. Default`true`

How to Use

Add the viewsUpload 1–4 images of the same object from different angles.
Choose texture and detailKeep Should Texture on for a textured model and pick standard or 2k Geometry Resolution.
Set mesh and character optionsAdjust Topology and Target Polycount; in Advanced settings add PBR, pose or rigging.
Run and inspectCheck the cost on Run, select Run, then rotate the GLB preview and download the files you need.

Pricing by option

Meshy 7.1 Multi Image to 3D is billed per generation from four parts: 160 credits for geometry, 80 for textures (should_texture true), 40 for rigging and 24 for animation. A request with default settings is textured and costs 240 credits ($1.200). Geometry resolution, model type, topology and polygon count do not change the price.

Generation	Cost	Billing unit
Textured (should_texture true, default)	$1.200 · 240 credits	160 base + 80 texture
Geometry only (should_texture false)	$0.800 · 160 credits	160 base
Add rigging	+$0.200 · +40 credits	enable_rigging true
Add animation	+$0.120 · +24 credits	enable_animation true, with rigging
Textured, rigged and animated	$1.520 · 304 credits	160 + 80 + 40 + 24

Use Cases

Product digitizationPhotograph a product from several sides and rebuild it for a catalog or configurator.
Props from reference shotsTurn turnaround photos of a physical prop into a game or film asset.
Shape checksRun untextured reconstructions to confirm proportions before final texturing.
Collectible archivesCapture toys and models from front, side and back views.

Pro Tips

Use views of the same object with the same lighting, such as front, side, back and three-quarter.
Keep the object at a similar size and centered in every image.
Two views already help with depth; add more when the back differs from the front.
Turn should_texture off for shape checks, then run a textured pass for the final asset.

Notes

Read every item in files: GLB is typically returned, with FBX, OBJ, USDZ or STL, textures and a thumbnail when available. Rigged and animated files are added when requested.
Rigging is designed for humanoid characters with clear limbs. Review the skeleton and weights in your 3D tool before production use.

Meshy 7.1 Multi Image to 3D related models

Meshy 7.1 Text to 3DCreate a 3D model from a written description.

Meshy 7.1 Image to 3DCreate a 3D model from one image.

Meshy 6 Multi Image to 3DThe previous Meshy generation at a lower price per model.

Meshy 7.1 Multi Image to 3D API frequently asked questions

What is the Meshy 7.1 Multi Image to 3D API?

Meshy 7.1 Multi Image to 3D is a Meshy model for reconstructing 3D assets from several views of one object. It combines 1–4 images into a textured model with up to 2K geometry, PBR maps, topology control and optional rigging. Using multiple angles of Meshy's 7.1 generation, it keeps the proportions and back surfaces closer to the real object. You can call it programmatically or try it from the playground above.

How many photos does Meshy 7.1 Multi Image to 3D accept?

Send 1–4 images of the same object. Front, side, back and three-quarter views give the reconstruction the most information about hidden surfaces.

Which geometry resolution does Meshy 7.1 Multi Image to 3D offer?

Choose standard or 2k with geometry_resolution. For 4K geometry from a single image, use Meshy 7.1 Image to 3D.

Can Meshy 7.1 Multi Image to 3D return an untextured model?

Yes. Set should_texture to false for geometry only at 160 credits. PBR maps and texture guidance are used with should_texture true.

How much does Meshy 7.1 Multi Image to 3D cost?

A default request is textured and costs 240 credits ($1.200). Geometry only costs 160 credits ($0.800); rigging adds 40 ($0.200) and animation adds 24 ($0.120). Resolution, topology and polygon count do not change the price.

How does Meshy 7.1 Multi Image to 3D rig and animate characters?

Set enable_rigging to true to add a humanoid skeleton, with rigging_height_meters for the character's height (default 1.7). Then set enable_animation to true and pick animation_action_id from 0 to 696 (default 92). A-pose or T-pose input helps the rig.

Which files does Meshy 7.1 Multi Image to 3D return?

Finished tasks list their files in files: typically a GLB, plus FBX, OBJ, USDZ or STL when available, texture maps and a thumbnail. Rigged and animated files are added when you request them.

How is Meshy 7.1 Multi Image to 3D different from Meshy 6 Multi Image to 3D?

Meshy 7.1 Multi Image to 3D belongs to Meshy's newer, detail-focused generation, with up to 2K geometry resolution and animation presets numbered 0–696. Meshy 6 Multi Image to 3D costs 60 credits ($0.300) per generation on Vidgo and suits quick drafts; Meshy 7.1 Multi Image to 3D costs 160–304 credits depending on options.