Meshy V7

https://mcp.app.layer.ai/mcp

execute_forge({
  "base_model_id": "meshy-v7",
  "prompt": "A wooden treasure chest with iron bands, game-ready",
  "batch_size": 1
})

# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/meshy-v7/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "A wooden treasure chest with iron bands, game-ready"
      }'

# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
  -H "Authorization: Bearer $LAYER_TOKEN"

prompt

string

Describe what to generate, or the change to make.

prompt_enhancement

enumdefault AUTOAUTO, OFF, STANDARD

Let the model rewrite the prompt before generating.

seed

integer

The starting point for the model's randomness. The same seed and settings give the same result.

face_limit

integerdefault 30000200–300000

The maximum number of faces in the output mesh.

quad_mesh

boolean

Build the mesh from four-sided faces, which are easier to edit and rig than triangles.

include_textures

booleandefault true

Paint colour onto the mesh. Off returns bare geometry.

pbr_materials

booleandefault false

Add metalness, roughness and normal maps so the model reacts to light in a game engine.

detailed_geometry

boolean

Sculpt finer surface detail into the mesh. Takes longer.

remesh_geometry

booleandefault true

Rebuild the raw sculpt as a cleaner, lighter mesh. Off keeps millions of faces.

enable_rigging

boolean

Add a skeleton so the model is ready to animate.

pose_mode

enumdefault NONENONE, A_POSE, T_POSE

The pose a character is built in. An A-pose or T-pose is easier to rig.

guidance_file_init_image

file[]

Views of the same subject, in any order

guidance_file_texture_image

file[]

Texture applied to the 3D model

prompt_language

string

The language the prompt is written in, so it reaches the model as you meant it.