Ludo AI Game Assets

Create 3D model

create3DModel

Convert a source image into a textured 3D model (image-to-3D). The job result is a downloadable GLB model_url plus an array of snapshot image URLs rendered from different angles (handy for previews). model picks the generator: prop (default) is low-cost and suits everyday props and environment pieces; hero is far more detailed and accurate, for close-up assets, but slower and more expensive. image is the front view; with prop, pass an optional back_image (the same subject seen from behind) so the back of the model follows it instead of being invented - hero takes the front image only and rejects a back_image with HTTP 400. The image is converted as it is: to make a character image for it first, from a prompt or by redrawing your own image as a 3D render, use create3DModelImage. Accepts optional mesh controls: target_num_faces (max triangle count, 1000-200000, default 50000), texture_size (1024 or 2048, default 2048), and texture_type ("pbr", "simple", or "none", default "pbr"). Pass rig true to also rig the model in the same call, with the general rig (joint_naming as in rigModel), ready for animate3DModelPreset or createDirectionalSprites; that adds the rigModel price, charged only when the result comes back rigged. Credits are held when the job is accepted and refunded if it fails or is cancelled. Pass an optional request_id to tag the result so you can locate it later via listGenerations (type 3d). Async generation job: returns {id, status} - poll getApiJob (job and credit contract: see the server instructions).

Credits: This endpoint consumes 4 credits per call with model "prop" (default), 15 credits per call with model "hero"; rig true adds 1 credit when the model comes back rigged.

Input Schema

Name	Required	Description	Default
`requestBody`	Yes	Payload for generating a 3D model from an image

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 28, 2026
- addedInput schema / properties / requestBody / description
```
Added value: +"Payload for generating a 3D model from an image"
```

Changed2 schema fields changedOct 16, 2026

changedInput schema / properties / requestBody / properties / rig / description

Previous value: -"Also rig the model (skeleton and skin weights) in the same call, as rigModel would, so it can be animated or rendered with createDirectionalSprites. Adds the rigModel price, charged only when the model comes back rigged (the result's rigged). Default: false."New value: +"Also rig the model (skeleton and skin weights) in the same call, so it can be animated or rendered with createDirectionalSprites. It gets the general rig, which suits any shape; there is no rig type to pick here (rigModel offers the others). Adds the rigModel price, charged only when the model comes back rigged (the result's rigged). Default: false."

removedInput schema / properties / requestBody / properties / rig_type

Removed value: -{
-  "description": "With rig, which skeleton to build (as rigModel's rig_type). humanoid_template (default, 22 joints) and humanoid_template_hands (52, five fingers per hand) suit two-armed, two-legged characters; general suits any shape. Animation presets and createDirectionalSprites' preset_id retarget onto any of them, though not onto every model. Default: \"humanoid_template\".",
-  "enum": [
-    "general",
-    "humanoid",
-    "game",
-    "humanoid_template",
-    "humanoid_template_hands"
-  ],
-  "example": "humanoid_template",
-  "type": "string"
-}

Changed1 schema field changedOct 16, 2026

changedInput schema / properties / requestBody / properties / rig_type / description

Previous value: -"With rig, which skeleton to build (as rigModel's rig_type). humanoid_template (default, 22 joints) and humanoid_template_hands (52, five fingers per hand) are the ones animation presets and createDirectionalSprites' preset_id need, and only suit two-armed, two-legged characters; use general for creatures and objects. Default: \"humanoid_template\"."New value: +"With rig, which skeleton to build (as rigModel's rig_type). humanoid_template (default, 22 joints) and humanoid_template_hands (52, five fingers per hand) suit two-armed, two-legged characters; general suits any shape. Animation presets and createDirectionalSprites' preset_id retarget onto any of them, though not onto every model. Default: \"humanoid_template\"."

Changed3 schema fields changedOct 15, 2026

addedInput schema / properties / requestBody / properties / joint_naming

Added value: +{
+  "description": "With rig, the bone naming convention (as rigModel's joint_naming). Purely a relabel - the skeleton is identical. Default: \"smpl\".",
+  "enum": [
+    "smpl",
+    "mixamo",
+    "humanik",
+    "unreal",
+    "godot",
+    "rigify",
+    "vroid"
+  ],
+  "example": "smpl",
+  "type": "string"
+}

addedInput schema / properties / requestBody / properties / rig

Added value: +{
+  "description": "Also rig the model (skeleton and skin weights) in the same call, as rigModel would, so it can be animated or rendered with createDirectionalSprites. Adds the rigModel price, charged only when the model comes back rigged (the result's rigged). Default: false.",
+  "example": false,
+  "type": "boolean"
+}

addedInput schema / properties / requestBody / properties / rig_type

Added value: +{
+  "description": "With rig, which skeleton to build (as rigModel's rig_type). humanoid_template (default, 22 joints) and humanoid_template_hands (52, five fingers per hand) are the ones animation presets and createDirectionalSprites' preset_id need, and only suit two-armed, two-legged characters; use general for creatures and objects. Default: \"humanoid_template\".",
+  "enum": [
+    "general",
+    "humanoid",
+    "game",
+    "humanoid_template",
+    "humanoid_template_hands"
+  ],
+  "example": "humanoid_template",
+  "type": "string"
+}

Changed2 schema fields changedOct 10, 2026

changedInput schema / properties / requestBody / properties / back_image / description

Previous value: -"Optional URL or base64-encoded image of the SAME subject seen from behind (rotated 180 degrees from image). The model's back then follows it instead of being invented from the front view alone. It must show the same subject, at the same scale and in the same pose and style as image. Only a back view is supported: a side or three-quarter view here produces a distorted model. No extra cost."New value: +"Optional URL or base64-encoded image of the SAME subject seen from behind (rotated 180 degrees from image). The model's back then follows it instead of being invented from the front view alone. It must show the same subject, at the same scale and in the same pose and style as image. Only a back view is supported: a side or three-quarter view here produces a distorted model. Prop model only: hero rejects it with HTTP 400. No extra cost."

addedInput schema / properties / requestBody / properties / model

Added value: +{
+  "description": "Model to use. Available models:\n- \"prop\" (Prop): 4 credits · Low-cost, good for everyday props and environment pieces\n- \"hero\" (Hero): 15 credits · Highly detailed, accurate 3D generation for close-up assets · front image only, no back_image. Default: \"prop\".",
+  "enum": [
+    "prop",
+    "hero"
+  ],
+  "example": "prop",
+  "type": "string"
+}

Changed2 schema fields changedSep 28, 2026

addedInput schema / properties / requestBody / properties / back_image

Added value: +{
+  "description": "Optional URL or base64-encoded image of the SAME subject seen from behind (rotated 180 degrees from image). The model's back then follows it instead of being invented from the front view alone. It must show the same subject, at the same scale and in the same pose and style as image. Only a back view is supported: a side or three-quarter view here produces a distorted model. No extra cost.",
+  "example": "<url> OR data:image/png;base64,...",
+  "type": "string"
+}

changedInput schema / properties / requestBody / properties / image / description

Previous value: -"URL or base64-encoded image to convert to 3D"New value: +"URL or base64-encoded image to convert to 3D, taken as the front view of the subject"

Changed1 schema field changedSep 18, 2026

changedInput schema / properties / requestBody / properties / request_id / description

Previous value: -"Optional client-provided identifier, unique per request. Re-sending the same request_id returns the existing job instead of generating again. Also usable with the results endpoint."New value: +"Optional client-provided identifier, unique per request. Re-sending the same request_id returns the existing job instead of generating again. Also usable as the request_id filter of listGenerations."

Changed1 schema field changedSep 17, 2026
- changedInput schema / properties / requestBody / properties / texture_size / example
```
Previous value: -1024New value: +2048
```
Changed6 schema fields changedSep 3, 2026
- removedInput schema / properties / requestBody / properties / target_num_faces / default
```
Removed value: -50000
```
- changedInput schema / properties / requestBody / properties / target_num_faces / description
```
Previous value: -"Maximum triangle count for the mesh (1000-200000)"New value: +"Maximum triangle count for the mesh (1000-200000) Default: 50000."
```
- removedInput schema / properties / requestBody / properties / texture_size / default
```
Removed value: -2048
```
- changedInput schema / properties / requestBody / properties / texture_size / description
```
Previous value: -"Texture resolution in pixels Accepted values: 1024, 2048."New value: +"Texture resolution in pixels Accepted values: 1024, 2048. Default: 2048."
```
- removedInput schema / properties / requestBody / properties / texture_type / default
```
Removed value: -"pbr"
```
- changedInput schema / properties / requestBody / properties / texture_type / description
```
Previous value: -"Texture type"New value: +"Texture type Default: \"pbr\"."
```

Changed1 schema field changedAug 30, 2026

changedInput schema / properties / requestBody / properties / request_id / description

Previous value: -"Optional client-provided identifier for this request. Use this to retrieve results later via the results endpoint."New value: +"Optional client-provided identifier, unique per request. Re-sending the same request_id returns the existing job instead of generating again. Also usable with the results endpoint."

Changed4 schema fields changedApr 10, 2026

removedInput schema / properties / requestBody / properties / high_detail_shape

Removed value: -{
-  "default": false,
-  "description": "Enable higher detail shape generation. Generation time will increase and the effect is only noticeable with a high target_num_faces value (around >30.000)",
-  "example": false,
-  "type": "boolean"
-}

changedInput schema / properties / requestBody / properties / target_num_faces / description

Previous value: -"Maximum triangle count for the mesh (1000-100000)"New value: +"Maximum triangle count for the mesh (1000-200000)"

changedInput schema / properties / requestBody / properties / target_num_faces / maximum
```
Previous value: -100000New value: +200000
```

changedInput schema / properties / requestBody / properties / texture_size / description

Previous value: -"Texture resolution in pixels Accepted values: 1024, 2048, 4096."New value: +"Texture resolution in pixels Accepted values: 1024, 2048."

Changed2 schema fields changedMar 4, 2026
- changedInput schema / properties / requestBody / properties / texture_size / description
```
Previous value: -"Texture resolution in pixels"New value: +"Texture resolution in pixels Accepted values: 1024, 2048, 4096."
```
- removedInput schema / properties / requestBody / properties / texture_size / enum
```
Removed value: -[
-  1024,
-  2048,
-  4096
-]
```

Changed1 schema field changedMar 3, 2026

addedInput schema / properties / requestBody / properties / request_id

Added value: +{
+  "description": "Optional client-provided identifier for this request. Use this to retrieve results later via the results endpoint.",
+  "type": "string"
+}

AddedFeb 2, 2026

TDQS

A4.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the write/async profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the bar is lower, and the description does add real value: credit hold/refund on failure, rig price charged only when the result comes back rigged, and the per-request_id dedupe behavior. What it does not disclose is anything about the polling lifecycle beyond 'poll getApiJob' — no timeout, failure states, or how long credits stay held — and the credit figures are stated twice (inline and in a trailing 'Credits:' line), which muddies rather than clarifies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded well — purpose, then return shape, then model choice, then optional controls — but it is a single dense block with genuine redundancy: the credit cost for prop/hero/rig is stated inline mid-paragraph and again in a trailing 'Credits:' sentence, and texture_size/target_num_faces ranges and defaults are repeated verbatim from the schema. The information is valuable but not tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an async, paid, multi-mode generation tool with no output schema, the description covers everything an agent needs to call it correctly: return shape `{id, status}`, the getApiJob polling path (deferring to server instructions for the credit contract), the credit hold/refund model and per-mode pricing, and the interlock between rig and the downstream animate3DModelPreset / createDirectionalSprites tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns one step above it by explaining the intent behind parameters rather than restating them — why back_image must be the same subject at the same scale/pose, what joint_naming actually means ('purely a relabel - the skeleton is identical'), and that rig uses the general rigModel rig with no type choice. Several details (ranges, defaults, enum meanings) merely duplicate the schema, which caps it below 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb and resource — 'Convert a source image into a textured 3D model (image-to-3D)' — and immediately declares the output artifacts (GLB model_url plus snapshot image URLs). It also names the sibling it is not (create3DModelImage) and explains what that sibling does instead, so an agent can discriminate without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit selection guidance for the model parameter (prop = cheap everyday props, hero = detailed close-up assets but slower/more expensive), plus a hard exclusion: hero 'takes the front image only and rejects a back_image with HTTP 400.' It also routes the agent to create3DModelImage when the source image itself needs to be generated, giving a when-to-use-this vs when-to-use-sibling decision path.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ludo AI Game Assets tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Create 3D model

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources