# Meshy V7 Text to 3D API

> Text-to-3D with Meshy 7: preview or full mode, 2k geometry, PBR, rigging and animation options

Generates a 3D model from a `prompt` of up to 600 characters, with optional `enable_prompt_expansion`. `mode` returns either untextured geometry or a textured model. Choose standard, lowpoly or smart-topology via `model_type`, set `target_polycount` from 100 to 300000, and pick standard or 2k `geometry_resolution`. Rigging and animation presets can be added for humanoid characters.

- Model id: `meshy/v7/text-to-3d`
- Made by: Meshy
- Category: Text to 3D
- Output: 3d
- Price per run: from $0.80 / run (cheapest run $0.80 (800 API credits))
- Run: `POST https://api.doitong.com/v1/run/meshy/v7/text-to-3d`
- Quote: `POST https://api.doitong.com/v1/quote/meshy/v7/text-to-3d`
- Docs page: https://doitong.com/developers/models/meshy/v7/text-to-3d

## Pricing

Price: **from $0.80 / run** (the lowest tier; the quote prices your exact input). Price per run: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $1.20 = 1200 API credits (1 run × $1.20).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/meshy/v7/text-to-3d` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | ≤ 600 characters | Description of the object to represent as a 3D model, limited to 600 characters. |
| `mode` |  | enum (string) | no | `full` | `preview`, `full` | Generation mode: 'preview' outputs geometry without textures, while 'full' outputs a textured model by combining preview and refine. |
| `seed` |  | integer \| null | no |  |  | Reuse this seed together with an unchanged prompt to usually reproduce an earlier result. |
| `model_type` |  | enum (string) | no | `standard` | `standard`, `lowpoly`, `smart-topology` | 3D mesh mode: choose 'lowpoly' for a low-poly result optimized for cleaner polygons; in this mode Meshy ignores topology, target_polycount, and should_remesh. For a conventional high-detail result choose 'standard', or choose 'smart-topology' to use Meshy-T2 during the geometry (preview) step and obtain clean parts generated separately from the outset. |
| `topology` |  | enum (string) | no | `triangle` | `quad`, `triangle` | Model topology choice between Triangle for geometric detail and Quad for surface smoothness. |
| `target_polycount` |  | integer | no | `30000` | 100 – 300,000 | Polygon-count target, capped at 15,000 when model_type is 'smart-topology'. Omitting the target in that mode selects Meshy's lower default of 4,000. |
| `should_remesh` |  | boolean | no | `true` |  | Skip remeshing and receive the raw triangular mesh by setting this to false; otherwise, enable the remesh phase. |
| `symmetry_mode` |  | enum (string) | no | `auto` | `off`, `auto`, `on` | Symmetry setting applied while generating the model. |
| `enable_pbr` |  | boolean | no | `false` |  | Controls generation of metallic, roughness, and normal PBR maps alongside the base color. |
| `is_a_t_pose` |  | boolean | no | `false` |  | T-pose generation switch activated by true; deprecated in favor of pose_mode. |
| `pose_mode` |  | enum (string) | no | `` | `a-pose`, `t-pose`, `` | Leave the string empty to avoid specifying the generated model's pose, or request an A-pose with 'a-pose' or a T-pose with 't-pose'. |
| `enable_prompt_expansion` |  | boolean | no | `false` |  | Allow a large language model to enrich the prompt with details. Enabling this expansion leaves the prompt's meaning unchanged. |
| `texture_prompt` |  | string \| null | no |  | ≤ 600 characters | Guide texturing with an extra text prompt in 'full' mode; other modes do not use it. |
| `texture_image_url` |  | string (image URL) \| null | no |  |  | 2D reference image for texture generation, applied only in 'full' mode. |
| `enable_rigging` |  | boolean | no | `false` |  | Automatic humanoid rigging, most effective for humanoid models whose limbs are clearly distinguishable. Enabling it rigs the generated model and supplies basic animations for walking and running. |
| `rigging_height_meters` |  | number | no | `1.7` | > 0 | Provide an estimated character height in meters when enable_rigging is true; otherwise, this value has no effect. |
| `enable_animation` |  | boolean | no | `false` |  | Whether the rigged model receives a preset animation, which requires enable_rigging to be true. |
| `animation_action_id` |  | integer | no | `92` |  | Meshy library animation preset ID, with available actions listed at https://docs.meshy.ai/en/api/animation-library. Validation and use apply only when enable_animation is true: values outside [0, 696] are rejected with a 422, and "Idle" corresponds to `0`. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Preprocessing safety-check switch: true makes an input safety check a prerequisite to processing. |
| `geometry_resolution` |  | enum (string) \| null | no |  | `standard`, `2k` | Mesh geometry resolution; the supported Meshy-7 options are standard and 2k. |
| `ultra_mode` |  | boolean | no | `false` |  | Deprecated option superseded by geometry_resolution, which wins if both are supplied; use geometry_resolution='2k' instead. |

File parameters (`texture_image_url`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/meshy/v7/text-to-3d?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/meshy/v7/text-to-3d?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/meshy/v7/text-to-3d", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "meshy/v7/text-to-3d",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "meshy/v7/text-to-3d",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1200,
    "usd": "1.20",
    "charged": 1200,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "animation_glb": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "animation_fbx": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "model_glb": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "thumbnail": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "model_urls": {
      "glb": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "fbx": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "obj": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "usdz": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "blend": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "stl": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      }
    },
    "texture_urls": [
      {
        "base_color": {
          "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
          "content_type": "image/jpeg",
          "file_name": "0-output.jpeg",
          "file_size": 1843200
        },
        "metallic": {
          "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
          "content_type": "image/jpeg",
          "file_name": "0-output.jpeg",
          "file_size": 1843200
        },
        "normal": {
          "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
          "content_type": "image/jpeg",
          "file_name": "0-output.jpeg",
          "file_size": 1843200
        },
        "roughness": {
          "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
          "content_type": "image/jpeg",
          "file_name": "0-output.jpeg",
          "file_size": 1843200
        }
      }
    ],
    "seed": 42,
    "prompt": "A rustic, antique wooden treasure chest with a curved, domed lid, constructed from weathered, dark brown planks exhibiting prominent wood grain and subtle distress. It's heavily reinforced with broad, dark grey, oxidized metal bands secured by numerous circular rivets. Ornate, dark iron decorative elements featuring swirling foliate patterns and dragon motifs adorn the corners and lid. A prominent, circular, intricately carved metal lock plate with a central keyhole dominates the front, flanked by two large, dark metallic pull rings.",
    "actual_prompt": "string",
    "rigged_character_glb": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "rigged_character_fbx": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "basic_animations": {
      "walking_glb": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "walking_fbx": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "walking_armature_glb": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "running_glb": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "running_fbx": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      },
      "running_armature_glb": {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      }
    },
    "rig_task_id": "string"
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `animation_glb` | object {url, content_type, file_name, file_size} \| null | Animation result containing the 3D model as GLB; the response omits this result unless enable_animation is true. |
| `animation_fbx` | object {url, content_type, file_name, file_size} \| null | Animation result containing the 3D model as FBX; the response omits this result unless enable_animation is true. |
| `model_glb` | object {url, content_type, file_name, file_size} | GLB file containing the generated 3D object. |
| `thumbnail` | object {url, content_type, file_name, file_size} \| null | Thumbnail showing a preview of the generated model. |
| `model_urls` | object {glb, fbx, obj, usdz, blend, stl} | Links to the 3D model in various formats. |
| `texture_urls` | array of object {base_color, metallic, normal, roughness} | Texture files represented as an array of objects. |
| `seed` | integer \| null | Seed value used during generation. |
| `prompt` | string | Text prompt supplied for generation. |
| `actual_prompt` | string \| null | Prompt actually applied to generation when prompt expansion was enabled. |
| `rigged_character_glb` | object {url, content_type, file_name, file_size} \| null | Rigging result delivered as a GLB character file; absent from the response unless enable_rigging is true. |
| `rigged_character_fbx` | object {url, content_type, file_name, file_size} \| null | Rigging result delivered as an FBX character file; absent from the response unless enable_rigging is true. |
| `basic_animations` | object {walking_glb, walking_fbx, walking_armature_glb, running_glb, running_fbx, running_armature_glb} \| null | Basic walk and run animations, included only if enable_rigging is true. |
| `rig_task_id` | string \| null | Identifier for the rigging task; included only if enable_rigging is true. |

## Related models

- [Meshy V7 Image to 3D](https://doitong.com/developers/models/meshy/v7/image-to-3d.md) (`meshy/v7/image-to-3d`): from $0.80 / run
- [Meshy V7 Multi Image to 3D](https://doitong.com/developers/models/meshy/v7/multi-image-to-3d.md) (`meshy/v7/multi-image-to-3d`): from $0.80 / run
- [Meshy 7 Retexture](https://doitong.com/developers/models/meshy/v7/retexture.md) (`meshy/v7/retexture`): from $0.30 / request
- [Meshy 6 Preview · Text to 3D](https://doitong.com/developers/models/meshy/v6-preview/text-to-3d.md) (`meshy/v6-preview/text-to-3d`): $0.80 / request
- [Meshy 6 · Text to 3D](https://doitong.com/developers/models/meshy/v6/text-to-3d.md) (`meshy/v6/text-to-3d`): $0.80 / request
- [Meshy 7.1 Text to 3D](https://doitong.com/developers/models/meshy/v7.1/text-to-3d.md) (`meshy/v7.1/text-to-3d`): from $0.80 / run
- [Hunyuan 3d](https://doitong.com/developers/models/hunyuan-3d/v3.1/rapid/text-to-3d.md) (`hunyuan-3d/v3.1/rapid/text-to-3d`): from $0.225 / request
- [Hunyuan 3D Pro Text to 3D](https://doitong.com/developers/models/hunyuan-3d/v3.1/pro/text-to-3d.md) (`hunyuan-3d/v3.1/pro/text-to-3d`): $0.375 / run

## Links

- HTML page: https://doitong.com/developers/models/meshy/v7/text-to-3d
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=meshy/v7/text-to-3d
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/meshy/v7/text-to-3d