Meshy V7 Text-to-3D turns text prompts into textured, PBR-ready 3D models with configurable geometry, topology, rigging, and animation for game assets, product visualization, 3D design, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$1.32per run
3D model output
Open preview to inspect the generated asset.
A stylized low-detail bronze desk lamp with a round base, curved neck, and conical shade, clean product design
3D model output
Open preview to inspect the generated asset.
A full-body futuristic sci-fi warrior standing in a neutral A-pose, wearing sleek segmented titanium armor with glowing blue energy lines, a sealed tactical helmet, reinforced boots, mechanical gauntlets, and a compact power core on the chest. Symmetrical design, clean silhouette, realistic proportions, highly detailed hard-surface modeling, isolated character, no weapons, no cape, no base, no environment.
Meshy V7 Text to 3D generates a 3D model directly from a text prompt. Describe the object you want to create, choose preview or full mode, configure geometry settings, and optionally enable PBR materials, Ultra Mode, and humanoid rigging.
Text-to-3D generation
Create a 3D model from a written object description.
Preview and full modes
Use preview for untextured geometry or full for a textured model.
Flexible geometry controls
Configure topology, target polygon count, remeshing, symmetry, and model type.
Multiple model types
Choose standard, lowpoly, or smart-topology depending on your downstream workflow.
Texture guidance in full mode
Use texture_prompt or texture_image to guide texture appearance when generating a full textured model.
Optional PBR and rigging
Generate PBR material maps in full mode and optionally rig suitable humanoid characters.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe the object to generate as a 3D model. Length: 1–600 characters. |
| mode | No | Generation mode: preview or full. preview returns untextured geometry; full returns a textured model. Default: full. |
| model_type | No | Geometry generation mode: standard, lowpoly, or smart-topology. Default: standard. smart-topology supports up to 15000 target polygons. |
| topology | No | Mesh topology for remeshed output: quad or triangle. Default: triangle. |
| target_polycount | No | Target polygon count. Range: 100–300000. Default: 30000. smart-topology accepts at most 15000. |
| should_remesh | No | Enable remeshing for cleaner topology. Default: true. |
| symmetry_mode | No | Controls symmetry during model generation: off, auto, or on. Default: auto. |
| enable_pbr | No | Generate metallic, roughness, and normal maps in full mode. Default: false. |
| pose_mode | No | Optional humanoid pose: a-pose or t-pose. Leave unselected for no specific pose. |
| texture_prompt | No | Optional text guidance for texture generation in full mode. Maximum length: 600 characters. |
| texture_image | No | Optional image to guide texture generation in full mode. |
| ultra_mode | No | Enable higher-fidelity standard geometry. Default: false. Cannot be combined with lowpoly or smart-topology. |
| enable_rigging | No | Automatically rig a suitable humanoid character. Default: false. |
| rigging_height_meters | No | Approximate character height in meters when rigging is enabled. Minimum: 0.01. Default: 1.7. |
| seed | No | Random seed for reproducible results. Use -1 for a random seed. Default: -1. |
preview for quick untextured geometry or full for textured output.standard, lowpoly, or smart-topology.texture_prompt or texture_image when generating in full mode.enable_pbr when metallic, roughness, and normal maps are needed.ultra_mode for higher-fidelity standard geometry.enable_rigging for suitable humanoid characters.-1 for random generation.Pricing depends on selected mode, ultra_mode, and whether enable_rigging is enabled.
| Configuration | Cost |
|---|---|
| Preview geometry | $0.88 |
| Full textured model | $1.32 |
| Full textured model with Ultra Mode | $1.54 |
| Auto-rigging | +$0.22 |
| Configuration | Cost |
|---|---|
| Preview geometry | $0.88 |
| Preview geometry + auto-rigging | $1.10 |
| Full textured model | $1.32 |
| Full textured model + auto-rigging | $1.54 |
| Full textured model with Ultra Mode | $1.54 |
| Full textured model with Ultra Mode + auto-rigging | $1.76 |
enable_pbr, model_type, topology, target_polycount, should_remesh, symmetry_mode, pose_mode, texture_prompt, texture_image, and seed do not add separate charges in the current pricing formula.
lowpoly or smart-topology for optimized geometry.preview mode for fast geometry checks before running full textured generation.full mode when you need textured output.texture_prompt to describe material details such as metal, leather, ceramic, fabric, plastic, or wood.texture_image when you need texture appearance to follow a visual reference.lowpoly for lightweight assets and smart-topology when cleaner optimized topology is needed.target_polycount at or below 15000 when using smart-topology.ultra_mode only with standard geometry.seed when comparing prompt or parameter changes.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/meshy/v7/text-to-3d with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for v7 Text To 3d below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"mode": "full",
"model_type": "standard",
"topology": "triangle",
"target_polycount": 30000,
"should_remesh": true,
"symmetry_mode": "auto",
"enable_pbr": false,
"pose_mode": "a-pose",
"ultra_mode": false,
"enable_rigging": false,
"rigging_height_meters": 1.7,
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/meshy/v7/text-to-3d" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/meshy/v7/text-to-3d";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"mode": "full",
"model_type": "standard",
"topology": "triangle",
"target_polycount": 30000,
"should_remesh": true,
"symmetry_mode": "auto",
"enable_pbr": false,
"pose_mode": "a-pose",
"ultra_mode": false,
"enable_rigging": false,
"rigging_height_meters": 1.7,
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"mode": "full",
"model_type": "standard",
"topology": "triangle",
"target_polycount": 30000,
"should_remesh": True,
"symmetry_mode": "auto",
"enable_pbr": False,
"pose_mode": "a-pose",
"ultra_mode": False,
"enable_rigging": False,
"rigging_height_meters": 1.7,
"seed": -1
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/meshy/v7/text-to-3d", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)v7 Text To 3d is a Meshy model for 3D asset generation, exposed as a REST API on WaveSpeedAI. Meshy V7 Text-to-3D turns text prompts into textured, PBR-ready 3D models with configurable geometry, topology, rigging, and animation for game assets, product visualization, 3D design, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/meshy/meshy-v7-text-to-3d.
v7 Text To 3d starts at $1.32 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `seed`, `enable_pbr`, `enable_rigging`, `mode`, `model_type`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/meshy/meshy-v7-text-to-3d.
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
Commercial usage rights depend on the model's license, set by its provider (Meshy). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.