Indsend asynkrone Rivya API-genereringsjobs med model, prompt, params, Idempotency-Key og offentlige svarfelter.

Brug POST /api/v1/generations til at indsende et asynkront billed-, video- eller audiogenereringsjob.

For chatmodeller skal du bruge Chat API. POST /api/v1/generations opretter ikke chat-sessioner eller assistant-beskeder.

Endpoint

POST https://rivya.ai/api/v1/generations

Påkrævede headers:

Authorization: Bearer rvya_sk_...
Content-Type: application/json

Anbefalet header:

Idempotency-Key: your-unique-request-key

Request body

{
  "model": "z-image",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "1:1"
  },
  "client_request_id": "order-123-preview"
}

Felter:

model: påkrævet offentlig model-ID
prompt: prompttekst, påkrævet af mange modeller
params: modelspecifikt parameterobjekt
client_request_id: valgfrit trace-ID fra dit system

Læs Model API Reference for modelspecifikke params.

For modeller, der accepterer uploadede referencemedier, skal du først kalde Files API. Send derefter uploadresultatet gennem modellens params; tilføj ikke et top-level files-felt til genereringsanmodningen.

Brug params.referenceMediaItems til nye integrationer:

{
  "model": "nano-banana-2",
  "prompt": "Restyle this product photo for a clean editorial catalog page",
  "params": {
    "referenceMediaItems": [
      {
        "url": "https://...",
        "kind": "image",
        "name": "reference.png",
        "mimeType": "image/png"
      }
    ]
  }
}

For audio- eller videoinputs, der kræver varighedsverifikation, skal du inkludere den duration_token, der returneres af /api/v1/files, som durationToken på den relaterede referenceMediaItems-post.

curl-eksempel

curl https://rivya.ai/api/v1/generations \
  -H "Authorization: Bearer rvya_sk_..." \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: product-preview-001" \
  -d '{
    "model": "z-image",
    "prompt": "A clean editorial product image on a soft studio background",
    "params": {
      "aspect_ratio": "1:1"
    }
  }'

JavaScript-eksempel

const response = await fetch("https://rivya.ai/api/v1/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.RIVYA_API_KEY}`,
    "Content-Type": "application/json",
    "Idempotency-Key": "product-preview-001"
  },
  body: JSON.stringify({
    model: "z-image",
    prompt: "A clean editorial product image on a soft studio background",
    params: { aspect_ratio: "1:1" }
  })
});

const generation = await response.json();
console.log(generation.id, generation.status);

Python-eksempel

import os
import requests

response = requests.post(
    "https://rivya.ai/api/v1/generations",
    headers={
        "Authorization": f"Bearer {os.environ['RIVYA_API_KEY']}",
        "Content-Type": "application/json",
        "Idempotency-Key": "product-preview-001",
    },
    json={
        "model": "z-image",
        "prompt": "A clean editorial product image on a soft studio background",
        "params": {"aspect_ratio": "1:1"},
    },
    timeout=30,
)

generation = response.json()
print(generation["id"], generation["status"])

Svar

{
  "id": "task_public_id",
  "status": "queued",
  "model": "z-image",
  "reserved_credits": 1,
  "final_credits": 0,
  "created_at": "2026-05-10T00:00:00.000Z",
  "updated_at": "2026-05-10T00:00:00.000Z",
  "result": null,
  "error": null
}

Gem id, og poll Genereringsstatus. Hvis du konfigurerer API Webhooks, kan Rivya også sende en signeret generation.succeeded- eller generation.failed-event, når opgaven når en terminal tilstand.

Idempotency

Brug Idempotency-Key til retries. Hvis samme key og samme request body afspilles igen, kan Rivya returnere det gemte offentlige svar i stedet for at oprette en dubletopgave.

Hvis samme key genbruges med et andet input, returnerer API'en idempotency_conflict.

Opret generation