# Meshy 7.1

> Run Meshy 7.1 by meshy online or via API. $0.0127/Meshy credit (20 base + 10-15 texture + 5 hi-res geo), no setup.

**URL:** https://inference.sh/apps/meshy/meshy-7-1
**Last updated:** 2026-10-28

---

Meshy 7.1 3D model generation from a text prompt, one image, or up to four views. Textured or bare mesh, PBR maps, quad or triangle topology, GLB, FBX, OBJ, STL, USDZ or 3MF.

- app: `meshy/meshy-7-1`
- maker: [meshy](https://inference.sh/apps/meshy.md)
- category: [3d](https://inference.sh/apps/category/3d.md)
- input → output: text → 3d, image → 3d
- tasks: [text to 3d](https://inference.sh/apps/tag/text-to-3d.md), [image to 3d](https://inference.sh/apps/tag/image-to-3d.md)
- price: $0.0127/Meshy credit (20 base + 10-15 texture + 5 hi-res geo)
- runs via: api, javascript and python sdk, belt cli, mcp

## meshy-7-1 API Guide

### About
meshy 7.1 3d model generation from a text prompt, one image, or up to four views. textured or bare mesh, pbr maps, quad or triangle topology, glb, fbx, obj, stl, usdz or 3mf.

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @522t8trd pinned
result = client.run({
        "app": "meshy/meshy-7-1@522t8trd",
        "input": {
            "prompt": "a weathered bronze statue of a fox sitting upright"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @522t8trd pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "meshy/meshy-7-1@522t8trd",
        "input": {
            "prompt": "a weathered bronze statue of a fox sitting upright"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "meshy/meshy-7-1@522t8trd",
        "input": {
            "prompt": "a weathered bronze statue of a fox sitting upright"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "meshy/meshy-7-1@522t8trd",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **prompt** (string): What to make, for Text to 3D. Used when no images are given.
- **images** (array): One image of the object, or two to four views of it with the front view first. jpg, png or webp.
- **should_texture** (boolean): Texture the mesh. Off returns the bare mesh and costs less.
- **enable_pbr** (boolean): Add metallic, roughness and normal maps. Needs should_texture.
- **texture_resolution** (string): Texture size. 8k costs more.
- **texture_prompt** (string): Text that guides the texture. Takes precedence over texture_image.
- **texture_image** (string): An image whose look the texture should follow.
- **geometry_resolution** (string): Mesh detail. 2k and 4k cost 5 credits more; 4k is not available with several images.
- **topology** (string): Polygon type of the mesh.
- **should_remesh** (boolean): Remesh to target_polycount and topology.
- **target_polycount** (integer): Polygon count when remeshing, 100 to 300000. Empty: 30000.
- **pose_mode** (string): Put a character in an A or T pose. Empty: as given.
- **image_enhancement** (boolean): Let Meshy clean up the input images first.
- **auto_size** (boolean): Scale the model to a real-world size.
- **origin_at** (string): Where the origin sits with auto_size.
- **format** (string): File format of the model.
- **moderation** (boolean): Have Meshy refuse harmful prompts and images.

#### Output
- **model** (string): The 3D model.
- **textures** (array): Texture maps: base color, and metallic, roughness and normal with PBR.
- **thumbnail** (string): A preview render of the model.

## other 3d apps

- [Tripo Auto Rig](https://inference.sh/apps/tripo/tripo-rig.md): $0.01/credit (rig check free, auto rig 25 credits, retarget 10 credits/animation)
- [Hunyuan 3D Auto Rigging](https://inference.sh/apps/tencent/hunyuan-3d-auto-rigging.md): $0.02/credit, 10 credits/call ($0.20/call)
- [Hunyuan 3D 3.1](https://inference.sh/apps/tencent/hunyuan-3d-3-1.md): $0.02/credit; Geometry 15cr, Normal 25cr, +10cr views/PBR/face-count
- [Rodin Gen-2.5](https://inference.sh/apps/hyper3d/rodin-gen-2-5.md): $0.58/credit; Extreme-High tier +0.5 credits, texture extreme-high +2 credits
- [Tripo 3.1](https://inference.sh/apps/tripo/tripo-3-1.md): $0.01/credit, $0.10-$0.50/run (text: 10-40 credits, image/multiview: 20-50 credits)

## faq

### how much does Meshy 7.1 cost?

$0.0127/Meshy credit (20 base + 10-15 texture + 5 hi-res geo). you pay per run from your inference shell credits. no subscription is required.

### how do I run Meshy 7.1 via api?

call meshy/meshy-7-1 with the javascript or python sdk, the rest api, or `belt app run meshy/meshy-7-1` from a terminal. the api reference on this page lists every input.

### who makes Meshy 7.1?

Meshy 7.1 is made by meshy and runs on inference shell. every meshy app is listed at https://inference.sh/apps/meshy.

### can my agent use Meshy 7.1?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to Meshy 7.1?

other 3d apps on inference shell include Tripo Auto Rig, Hunyuan 3D Auto Rigging, Hunyuan 3D 3.1, Rodin Gen-2.5. they run through the same api, so switching is a one-line change.