Every AI model.
One API. One bill.

# Same request shape for every model. Change "model" to switch.
curl https://api.tovano.ai/v1/tasks \
  -H "Authorization: Bearer $TOVANO_API_KEY" \
  -H "X-Tovano-Customer: client-0482" \
  -d '{
    "model": "image/demo-1",
    "input": { "prompt": "Product photo of a blue ceramic mug", "n": 4 }
  }'

# → { "id": "tsk_9f2c…", "status": "completed", "unit": "image", "units": 4, "charged_micro": 80000 }

// npm install tovano
import Tovano from "tovano";

const tovano = new Tovano(); // reads TOVANO_API_KEY

const task = await tovano.tasks.create({
  model: "image/demo-1",
  input: { prompt: "Product photo of a blue ceramic mug", n: 4 },
  customer: "client-0482",
});

const done = await tovano.tasks.wait(task.id);
console.log(done.output.images, done.charged_micro); // 80000 = $0.080

import os, requests

r = requests.post(
    "https://api.tovano.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['TOVANO_API_KEY']}"},
    json={
        "model": "image/demo-1",
        "input": {"prompt": "Product photo of a blue ceramic mug", "n": 4},
        "customer": "client-0482",
    },
)
task = r.json()
print(task["id"], task["status"])

// Text models speak the OpenAI format. Point any OpenAI client at Tovano.
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.tovano.ai/v1",
  apiKey: process.env.TOVANO_API_KEY,
});

const reply = await client.chat.completions.create({
  model: "text/demo-chat-1",
  messages: [{ role: "user", content: "Three captions for a mug ad" }],
  stream: true,
});