Create a key
Sign in and open API Keys in Settings. Create a key, review its permissions, and save the full secret when it is shown; you cannot reveal it again.
Rivya API
Generation quickstart
Models
API model catalog
Billing
Shared credits
Requests
Async jobs + chat
Access
API keys
Replace the placeholder with your Rivya API key and make sure your account has enough credits. This example shows a Z-Image job; other models have their own input and credit requirements.
curl https://rivya.ai/api/v1/generations \
-H "Authorization: Bearer rvya_sk_..." \
-H "Content-Type: application/json" \
-H "Idempotency-Key: demo-job-001" \
-d '{
"model": "z-image",
"prompt": "Editorial product photo on a clean studio set"
}'{
"id": "task_public_id",
"status": "queued",
"model": "z-image",
"reserved_credits": 1,
"final_credits": 1,
"settlement_status": "RESERVED",
"created_at": "2026-05-11T00:00:00.000Z",
"updated_at": "2026-05-11T00:00:00.000Z",
"result": null,
"error": null
}API debugger
Start with a mock preview, then sign in to test a real request. The generation selector lists non-chat models that accept text without reference media. Use the Files panel to test reference uploads with your own API key, and find chat examples in the API docs.
Account status
Checking your account…
API key prefix
—
Current credits
—
Mock mode never calls a model or consumes credits. Credit values illustrate the model's base cost; they are not a quote for your prompt or parameters.
Paste your full API key to send live requests from this debugger. It stays in this page's memory until you reset or refresh the page.
Files API upload test
Upload reference media through POST /api/v1/files. For a generation model that supports references, use the generated params.referenceMediaItems below and preserve the returned metadata and signed tokens.
The selected model determines the allowed media types, file size, duration, and dimensions. A live upload sends the file to the upload service using your API key. Mock metadata is illustrative; only a live upload provides usable signed tokens.
{
"model": "z-image",
"prompt": "Editorial product photo on a clean studio set",
"params": {
"aspect_ratio": "1:1"
}
}{
"id": "mock_task_001",
"status": "queued",
"model": "z-image",
"reserved_credits": 1,
"final_credits": 1,
"settlement_status": "RESERVED",
"created_at": "2026-05-11T00:00:00.000Z",
"updated_at": "2026-05-11T00:00:00.000Z",
"result": null,
"error": null
}{
"id": "file_mock_001",
"object": "file",
"kind": "image",
"file_name": "reference.png",
"mime_type": "image/png",
"size_bytes": 245760,
"url": "https://media.example/reference.png",
"duration_seconds": null,
"duration_token": null,
"width": 1024,
"height": 1024,
"image_dimensions_token": "mock_not_a_valid_image_dimensions_token",
"video_width": null,
"video_height": null,
"frames_per_second": null,
"video_bitrate_mbps": null,
"video_file_size_bytes": null,
"video_metadata_token": null,
"created_at": "2026-05-11T00:00:00.000Z",
"expires_at": null
}{
"params": {
"referenceMediaItems": [
{
"url": "https://media.example/reference.png",
"kind": "image",
"name": "reference.png",
"mimeType": "image/png",
"width": 1024,
"height": 1024,
"sizeBytes": 245760,
"imageDimensionsToken": "mock_not_a_valid_image_dimensions_token"
}
]
}
}Task status
Model base credits
1
Status
Queued
Get started
Sign in and open API Keys in Settings. Create a key, review its permissions, and save the full secret when it is shown; you cannot reveal it again.
Read the API model reference or call GET /api/v1/models. Check availability, model ID, parameters, supported inputs, chat capabilities, and pricing before submitting.
For generation, include an idempotency key and poll the task endpoint, or configure signed webhooks when enabled. For chat, send a turn and receive either a standard response or an SSE stream.
API capabilities
Use Rivya model IDs and your account credits across the API and Studio. Check each model's API status, inputs, and pricing before submitting; a catalog listing alone does not mean a model is callable.
Submit an image job with a prompt and the model's supported parameters. Poll its task status to retrieve the result.
Submit asynchronous video jobs with supported text or reference inputs. Track progress through task status or signed webhooks when enabled.
Call available audio models using their supported inputs and parameters. Audio jobs use your Rivya account credits and task history.
API and Studio usage draw from the same balance. Generation jobs reserve credits before processing and report the final charge after settlement.
Public API v1
Use the API docs to check endpoint requirements and each model's supported inputs before you integrate.
Send chat turns and receive either a standard response or an SSE stream. Sessions are created through the API, and supported models can accept image attachments uploaded through the Files API.
Upload reference images, videos, or audio for supported models. Preserve the returned URL, metadata, and signed tokens when building params.referenceMediaItems; chat attachments use file_id values.
When webhooks are enabled, configure an endpoint to receive signed callbacks when a generation task succeeds or fails. Verify the signature before processing an event.
Learn how to authenticate requests, choose model parameters, handle responses, reuse idempotency keys, and interpret error codes.
Open docsCreate a key in Settings and copy its secret when it is shown. To replace a key, create a new one and revoke the old key.
Manage keysPreview the request flow with mock responses. Live generation requests require sign-in, an API key, and enough account credits.
Open the debugger