promptstringRequiredText-driven reconstruction: Required object description, at most 1,024 characters; include complete shape, material, colour, style and scale.
- Default
- Not specified
- Constraints
- minLength:1maxLength:1024
tripo/h3.1/text-to-3dTripo H3.1 Text to 3D turns a written object description into a 3D asset, normally a GLB with textures. It first creates a reference picture, then builds the object from that picture. The additional `image_seed` belongs to that first visual step, while the geometry and texture stages have their own seeds.
Examples use the selected endpoint’s public parameter definitions. Replace the API key and example media, then send the request from your server.
SDKs & integrationshttps://api.spicyapi.ai/api/v1/jobs/createTaskKeep the API key in the server environment variable SPICY_API_KEY. Use Bearer authentication and Content-Type: application/json for JSON requests.
Authorization: Bearer $SPICY_API_KEY# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "tripo/h3.1/text-to-3d",
"input": {
"prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
"low_poly": false,
"quad_mesh": false,
"generate_pbr": true,
"generate_parts": false,
"texture_quality": "standard"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"Generated from this model’s input schema — the same one the API validates every request against.
Place these fields inside the request body’s input object. Names and types match the API. Do not assume a default when none is specified.
promptstringRequiredText-driven reconstruction: Required object description, at most 1,024 characters; include complete shape, material, colour, style and scale.
texture_seedintegerOptionalText-driven reconstruction: Texture-stage seed for controlled surface comparisons, without an identical-output guarantee.
image_seedintegerOptionalText-driven reconstruction: Seed for the reference-image stage before 3D reconstruction; compare one change without assuming exact repetition.
seedintegerOptionalText-driven reconstruction: Geometry seed for comparisons where you change one setting at a time; exact repetition is not assured.
uv_unwrapbooleanOptionalText-driven reconstruction: On by default; disabling UV export reduces processing and size but removes coordinates needed for later texturing.
auto_sizebooleanOptionalText-driven reconstruction: Off by default; estimates real-world scale and requires textured output.
face_limitintegerOptionalText-driven reconstruction: Target 1,000–2,000,000 faces for the text-generated mesh; with low_poly, stay at or below 20,000.
generate_partsbooleanOptionalAffects priceText-driven reconstruction: Separates the object into untextured triangular parts; texture and quad settings are ignored and their charges replaced by the parts add-on.
low_polybooleanOptionalAffects priceText-driven reconstruction: Handcrafted-style low-poly processing; a face_limit no higher than 20,000 is recommended and a dedicated add-on applies.
quad_meshbooleanOptionalAffects priceText-driven reconstruction: Produces quad topology in FBX instead of GLB; ignored and not charged with generate_parts.
geometry_qualitystringOptionalAffects priceText-driven reconstruction: standard or detailed; detailed adds surface-geometry processing and its own charge.
"standard""detailed"remove_lightingbooleanOptionalText-driven reconstruction: On by default, but only effective with v3.5; removes lighting baked into the reference texture.
texture_versionstringOptionalText-driven reconstruction: Choose v3.0-20250812 (default) or v3.5-20260815; fast and lighting removal use v3.5.
"v3.0-20250812""v3.5-20260815"texture_qualitystringOptionalAffects priceText-driven reconstruction: standard is the default; detailed and extreme (8K) add quality charges; fast uses v3.5 at the standard rate; no quality charge without textures.
"standard""detailed""extreme""fast"generate_pbrbooleanOptionalAffects priceText-driven reconstruction: On by default; PBR materials enable texturing even when generate_texture is off.
generate_texturebooleanOptionalAffects priceText-driven reconstruction: On by default; adds colour textures, and a plain mesh requires generate_pbr to be off as well.
negative_promptstringOptionalText-driven reconstruction: Optional short exclusions, at most 255 characters, such as base or pedestal.
{
"type": "object",
"required": [
"prompt"
],
"x-pricing": {
"billingMode": "formula",
"variantFields": []
},
"properties": {
"seed": {
"type": "integer",
"x-ui": {
"order": 20,
"widget": "number",
"advanced": true
},
"maximum": 2147483647,
"minimum": 0,
"description": "Seed for the geometry step, for reproducible shapes."
},
"prompt": {
"type": "string",
"x-ui": {
"order": 100,
"widget": "textarea",
"primary": true
},
"maxLength": 1024,
"minLength": 1,
"description": "Describe the object to build: shape, material, colour, style and scale. One object, fully visible. Up to 1,024 characters."
},
"low_poly": {
"type": "boolean",
"x-ui": {
"order": 68,
"widget": "switch",
"affects_price": true
},
"default": false,
"description": "Build a low-poly mesh with clean, hand-modelled-style topology instead of a dense scan-like one. Best for simple objects; keep face_limit at 20,000 or below with it. Off by default; adds to the price."
},
"auto_size": {
"type": "boolean",
"x-ui": {
"order": 30,
"widget": "switch",
"advanced": true,
"affects_price": false
},
"default": false,
"description": "Scale the mesh to estimated real-world dimensions. Off by default."
},
"quad_mesh": {
"type": "boolean",
"x-ui": {
"order": 70,
"widget": "switch",
"affects_price": true
},
"default": false,
"description": "Return four-sided (quad) polygons instead of triangles, for editing in modelling tools; the file then comes back as FBX instead of GLB. Off by default; adds to the price. Ignored when generate_parts is on."
},
"uv_unwrap": {
"type": "boolean",
"x-ui": {
"order": 25,
"widget": "switch",
"advanced": true,
"affects_price": false
},
"default": true,
"description": "Unwrap UV coordinates during generation. On by default; turning it off is faster and gives a smaller file, but the mesh then has no UVs for texturing later. Does not change the price."
},
"face_limit": {
"type": "integer",
"x-ui": {
"step": 1000,
"order": 65,
"widget": "slider",
"affects_price": false
},
"maximum": 2000000,
"minimum": 1000,
"description": "Target face count, 1,000 to 2,000,000. Leave empty to let the model decide (often over a million faces). Does not change the price."
},
"image_seed": {
"type": "integer",
"x-ui": {
"order": 15,
"widget": "number",
"advanced": true
},
"maximum": 2147483647,
"minimum": 0,
"description": "Seed for the first step, which draws a reference picture from the prompt. Keep it fixed to keep the same starting picture."
},
"generate_pbr": {
"type": "boolean",
"x-ui": {
"order": 85,
"widget": "switch",
"affects_price": true
},
"default": true,
"description": "Add PBR material maps (metal-roughness and normal). On by default and switches texturing on."
},
"texture_seed": {
"type": "integer",
"x-ui": {
"order": 10,
"widget": "number",
"advanced": true
},
"maximum": 2147483647,
"minimum": 0,
"description": "Seed for the texture step. Keep seed fixed and change this to try new textures on the same shape."
},
"generate_parts": {
"type": "boolean",
"x-ui": {
"order": 67,
"widget": "switch",
"affects_price": true
},
"default": false,
"description": "Return the model split into separate, editable parts. Parts are untextured triangle meshes, so the texture options and quad_mesh are ignored and not charged. Off by default; costs more than the textured default."
},
"negative_prompt": {
"type": "string",
"x-ui": {
"order": 96,
"widget": "textarea",
"advanced": true
},
"maxLength": 255,
"description": "What the object should not have, written as a short list. Up to 255 characters."
},
"remove_lighting": {
"type": "boolean",
"x-ui": {
"order": 77,
"widget": "switch",
"affects_price": false
},
"default": true,
"description": "Remove the lighting and shadows baked into the picture before texturing, so the texture reacts cleanly to scene lights. On by default; only takes effect with the v3.5 texture model. Does not change the price."
},
"texture_quality": {
"enum": [
"standard",
"detailed",
"extreme",
"fast"
],
"type": "string",
"x-ui": {
"order": 80,
"widget": "radio",
"enum_labels": {
"fast": "Fast",
"extreme": "8K",
"detailed": "Detailed",
"standard": "Standard"
},
"affects_price": true
},
"default": "standard",
"description": "Texture quality: standard (the default), detailed (higher resolution), extreme (8K) or fast (standard size, generated quicker with the v3.5 texture model). detailed and extreme cost more and only apply to textured meshes."
},
"texture_version": {
"enum": [
"v3.0-20250812",
"v3.5-20260815"
],
"type": "string",
"x-ui": {
"order": 78,
"widget": "radio",
"enum_labels": {
"v3.0-20250812": "v3.0",
"v3.5-20260815": "v3.5"
},
"affects_price": false
},
"default": "v3.0-20250812",
"description": "Texture model version: v3.0-20250812 (the default) or the newer v3.5-20260815. texture_quality fast and remove_lighting use v3.5. Does not change the price."
},
"generate_texture": {
"type": "boolean",
"x-ui": {
"order": 90,
"widget": "switch",
"affects_price": true
},
"default": true,
"description": "Paint a texture onto the mesh. On by default; turning it off only removes texturing if generate_pbr is off too."
},
"geometry_quality": {
"enum": [
"standard",
"detailed"
],
"type": "string",
"x-ui": {
"order": 75,
"widget": "radio",
"enum_labels": {
"detailed": "Detailed",
"standard": "Standard"
},
"affects_price": true
},
"default": "standard",
"description": "Geometry detail: standard (the default) or detailed. detailed builds finer surface detail and costs more."
}
},
"additionalProperties": false
}HTTP 202 means the task was accepted, not completed. Save the returned taskId and query that task. Do not create another task while waiting for its result.
HTTP/1.1 202 Accepted
Location: /api/v1/jobs/recordInfo?taskId=job_01k3m8x9q2z4v7n5p6r8s0t1w3
{
"code": 200,
"msg": "success",
"request_id": "req_example_create",
"data": {
"taskId": "job_01k3m8x9q2z4v7n5p6r8s0t1w3",
"state": "queued",
"estimatedCost": "0.750000"
}
}The accepted response includes the estimate so your app can show the same amount in task history and billing.
curl --get "https://api.spicyapi.ai/api/v1/jobs/recordInfo" \
--data-urlencode "taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"Start polling at about 2 seconds and gradually increase the interval. Stop at a terminal state. After a connection failure, query the original taskId. Retry creation only with the original idempotency key and body.
import { verifyWebhook } from "@spicyapi/sdk";
// express.raw keeps the bytes we signed; express.json never matches.
app.post("/hooks/spicy", express.raw({ type: "application/json" }), (req, res) => {
const { payload } = verifyWebhook({
rawBody: req.body,
timestamp: req.header("X-Webhook-Timestamp"),
signature: req.header("X-Webhook-Signature"),
payloadVersion: Number(req.header("X-Webhook-Payload-Version")),
secret: process.env.SPICY_WEBHOOK_SECRET,
});
res.status(200).end();
void handleFinishedTask(payload);
});Pass callBackUrl when you create the task and the finished record is POSTed to you — no polling loop at all. Every delivery carries X-Webhook-Timestamp, X-Webhook-Signature and X-Webhook-Payload-Version. The signature is a base64 HMAC-SHA256 over taskId.timestamp.sha256(body), so it must be checked against the raw bytes: parsing the JSON and re-serialising it changes them and the check will fail. Failed deliveries are retried, so the same taskId can arrive twice — make the handler idempotent. Answer 2xx first and do the work afterwards; a slow handler is treated as a failed delivery.
Consume output only when state is succeeded. On failure, use errorCode, errorMessage and request_id to investigate. Example costs and states do not represent an actual bill.
{
"code": 200,
"msg": "success",
"request_id": "req_example_record",
"data": {
"taskId": "job_01k3m8x9q2z4v7n5p6r8s0t1w3",
"model": "tripo/h3.1/text-to-3d",
"state": "succeeded",
"output": {
"assets": [
{
"key": "tasks/2026/08/28/job_01k3m8x9q2z4v7n5p6r8s0t1w3/3f7a1c9e5b2d48f0a6c1e3d5b7f9a1c3.png",
"mime": "image/png",
"url": "https://example.r2.cloudflarestorage.com/results/job_01k3m8x9q2z4v7n5p6r8s0t1w3/result.png?X-Amz-Signature=SIGNATURE_FROM_RESPONSE",
"expiresAt": "2026-08-28T12:20:08.000Z"
}
]
},
"cost": "0.750000",
"settled": true,
"createdAt": "2026-08-28T12:00:00Z",
"completedAt": "2026-08-28T12:00:30Z"
}
}For each available asset, open or download assets[].url directly without an API Authorization header. The signed URL expires at expiresAt; poll the task again to refresh it while the asset remains within its retention period. A pending or unavailable asset has no URL. Treat signed URLs as private.
Use SpicyAPI in your app, terminal, AI assistant or visual workflow. Choose a setup guide below.
You do not have to write any of the code above. Connect the MCP server once and any agent that speaks MCP — Claude Code, Codex, Cursor, Windsurf, VS Code, Gemini CLI, Cline, LibreChat — can run this model by name, or run it from your shell with a single command.
Use tripo/h3.1/text-to-3d to generate a portrait of a dancer under neon light, and save it to ./out/.
The agent looks the model up in the live catalogue, uploads the local file for you, then shows the exact quote and its maximum charge and waits for your confirmation. Nothing is billed until you say yes.
claude mcp add spicyapi -e SPICY_API_KEY=$SPICY_API_KEY \
-- npx --yes --package=@spicyapi/mcp spicyapi-mcp
npx skills add spicyapi-ai/spicy-skillThe first line gives the agent the tools; the second gives it the Skill — the operating rules for them, so it quotes before it bills, uploads local files instead of pasting bytes, and reads the finished asset URL rather than guessing. Every other client takes the same server through its own config file: see the developer hub.
npx @spicyapi/cli tasks create --model tripo/h3.1/text-to-3d \
--input-json '{"prompt":"A ceramic teapot on a linen cloth, soft window light, muted palette","low_poly":false,"quad_mesh":false,"generate_pbr":true,"generate_parts":false,"texture_quality":"standard"}' \
--waitThe input is this endpoint’s own schema, same as the examples above. --wait polls until the task is finished and prints it; add --yes to skip the confirmation prompt in CI. Set SPICY_API_KEY first — one key works for the API, the CLI and the MCP server.
npx @spicyapi/cli tasks create --model tripo/h3.1/text-to-3d \
--input-json '{…}' --retention 1h --wait
npx @spicyapi/cli tasks get $TASK_ID # read back the retention that applied--retention only ever shortens the window — 30m, 1h, 7d, or 0 to delete as soon as the task reaches a terminal state. The value that actually applies is the shortest of your request, your account settings and the platform maximum, so read it back from the task record rather than assuming the number you asked for took effect. Passing a longer window than your account allows does nothing.
Install the SpicyAPI nodes from ComfyUI Manager or with the command below, then search for Tripo H3.1 · Text to 3D on the canvas. The node has the same options as this page and shows its price before it runs.
cd ComfyUI/custom_nodes
git clone https://github.com/spicyapi-ai/comfyui-spicyapiThe embedded panel reads the same schema as this page, so it cannot drift from the API. If your docs need the content to be searchable, read the JSON under /api/embed/models/ and render it yourself.
<iframe src="https://spicyapi.ai/embed/en/models/tripo-h3-1/api?model=tripo%2Fh3.1%2Ftext-to-3d" width="100%" height="560" loading="lazy" title="Request example" style="border:1px solid rgba(0,0,0,.12)"></iframe>