Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Meshy: Meshy-6

Meshy-6 is a 3D generation model for text-to-3D and image-to-3D workflows. It is built for cleaner geometry, sharper hard-surface detail, low-poly generation, configurable quad or triangle topology, polycount and symmetry control, A/T pose support, and textured outputs with optional PBR materials. It fits game asset creation, 3D printing, and production-oriented 3D pipelines.
Compare models
meshy-6
AvailableMeshy3DAsync
Price
From $0.80
Modalities
3D

About Meshy-6

Meshy-6 is a 3D generation model from Meshy that builds textured 3D assets from a text prompt or a single image. It is aimed at game assets, 3D printing, and production pipelines, and gives explicit control over mesh structure: quad or triangle topology, target polygon count, symmetry, and A-pose or T-pose characters. Textures can include PBR maps, and results export to common 3D formats.

Where it works well

  • Mesh controls are part of the request: quad or triangle topology and a target polygon count let you match an engine budget without a separate remeshing step.
  • Text-to-3D works in two stages, an untextured preview to judge the shape first and a refine pass to add texture, so a bad silhouette is caught before texturing.
  • Image-to-3D follows a reference picture closely, which suits concept art and product photos where the shape is already decided.
  • A-pose and T-pose output makes humanoid characters easier to rig and animate.
  • Optional PBR maps (metallic, roughness, normal) and several export formats, including GLB, OBJ, FBX, STL, USDZ and 3MF, fit both game and printing workflows.

When to choose another model

  • It returns a single object per request; full scenes with many separate items need to be built from several generations.
  • Image input works best with one clear subject on a plain background, so cluttered photos need background removal first.
  • Newer Meshy generations exist for the highest-precision geometry, so pick those when maximum detail matters more than a settled, widely used model.

Getting started

  1. Create API key

    Create a key in Console, then use it with every model on the platform.

  2. Send your first request

    Copy the example for your language and run it against the endpoint.

    Image to 3DText to 3DTokenLab endpoint
    POST/v1/3d/generations
    curl -X POST "https://api.tokenlab.sh/v1/3d/generations" \
      -H "Authorization: Bearer sk-xxx" \
      -H "Content-Type: application/json" \
      -d '{
      "model": "meshy-6",
      "prompt": "A stylized ceramic astronaut figurine."
    }'

Parameters

Image to 3D

ParameterValues and limitsDefaultNotes
formatglbglbNot provided
imageInputs: ≤ 1Not providedLimits apply when this input is supplied. The public API accepts one image string. Multiple image arrays are not exposed.
image_urlInputs: ≤ 1Not providedLimits apply when this input is supplied. The public API accepts one image string. Multiple image arrays are not exposed.
n11Use an integer.
operationRequiredNot providedNot providedNot provided
output_formatglbglbNot provided
prompt
Do not send prompt for image-to-3d. The active route rejects it. Supply image or image_url without prompt. For a text prompt, select text-to-3d and omit image inputs; the upstream requires text and source-image generation inputs to be separate.

Text to 3D

ParameterValues and limitsDefaultNotes
formatglbglbNot provided
imageInputs: ≤ 1Not providedLimits apply when this input is supplied. The public API accepts one image string. Multiple image arrays are not exposed.
image_urlInputs: ≤ 1Not providedLimits apply when this input is supplied. The public API accepts one image string. Multiple image arrays are not exposed.
n11Use an integer.
operationRequiredNot providedNot providedNot provided
output_formatglbglbNot provided
promptNot providedNot providedMaximum length: 600 characters.

Fields outside this contract are rejected.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Image to 3D

per request
Official price
$0.80
Verified price
—
Discount
—

Text to 3D

per request
Official price
$0.80
Verified price
—
Discount
—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours
Requests
Success rate
P95 latency
Total tokens
Model performance
Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Meshy-6 in Console with a prompt ready to edit or send.

Help me create with meshy-6 using text-to-3d at /v1/3d/generations. Show the result, status, and cost.

Use cases

  • Game props and characters

    Generate a prop or character with a polygon budget and quad topology, then drop it into an engine; use T-pose output for characters that will be rigged.

  • 3D printing prototypes

    Turn a sketch or product photo into a mesh and export STL or 3MF to print a prototype of a shape before modeling it by hand.

  • Concept exploration

    Run several text prompts for the same idea, compare the untextured previews, and refine only the silhouette you like.

  • E-commerce and AR assets

    Convert product photos into textured models exported as USDZ or GLB for viewers that show a product in 3D.

Prompt examples

A weathered bronze lantern with a hinged glass door, hard-surface detail, game-ready, clean quad topology.

Low-poly stylized fox character standing in a T-pose, flat colors, no accessories.

A sci-fi supply crate with worn paint and metal edges, PBR materials, symmetrical.

FAQ

Does Meshy-6 take text or images?

Both. Text-to-3D builds a model from a written description, and image-to-3D builds one from a reference picture. Image input is more predictable because the picture fixes the shape; text input is better for exploring ideas when you have no reference.

Can I control the polygon count and topology?

Yes. The request can ask for quad or triangle topology and a target polygon count, plus symmetry and pose options. These settings help match a mesh to a game engine budget or an animation rig.

Does it produce textures and PBR materials?

It produces textured models, and you can switch on PBR maps for metallic, roughness and normal data. For text prompts the texture comes from a refine step run after the untextured preview.

Which file formats can I export?

Meshy's API lists GLB, OBJ, FBX, STL, USDZ and 3MF as target formats. Pick GLB or FBX for engines, STL or 3MF for printing, and USDZ for Apple AR viewers.

Is Meshy-6 the newest Meshy model?

No. Meshy's documentation also lists newer 7-series models. Meshy-6 is still a sensible choice when you want its established behavior and topology options, and the quad or triangle, polycount and pose controls are all available on it.

How much does Meshy-6 cost?

On TokenLab, Meshy-6 costs $0.80 per request. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Meshy-6 use?

Use https://api.tokenlab.sh/v1/3d/generations for Meshy-6. The request example below shows the matching code shape.

Which operations does Meshy-6 support?

Meshy-6 supports Image to 3D, Text to 3D. Select an operation above to see its endpoint and request example.

Compare Meshy-6

Sources

Reviewed Oct 2, 2026

Related models