Chat

Text models use the OpenAI chat completions format. Any OpenAI client works: set the base URL to https://api.tovano.ai/v1 and use your Tovano key.

Request

curl https://api.tovano.ai/v1/chat/completions \
  -H "Authorization: Bearer $TOVANO_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Tovano-Customer: client-0482" \
  -d '{
    "model": "text/demo-chat-1",
    "messages": [
      { "role": "system", "content": "You write short ad copy." },
      { "role": "user", "content": "Three captions for a mug ad" }
    ]
  }'

With an OpenAI client

import OpenAI from "openai";

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

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

for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");

Streaming

With "stream": true the reply comes as server-sent events, one data: line per piece, and ends with data: [DONE]. The last chunk before [DONE] carries usage and the charge:

{
  "usage": { "prompt_tokens": 42, "completion_tokens": 61, "total_tokens": 103 },
  "tovano": { "task_id": "tsk_c81d...", "charged_micro": 58 }
}

Charges

You pay for input tokens at the model's input price and output tokens at its output price. charged_micro: 58 above is $0.000058. Every chat call is recorded as a task, so it shows up in Tasks and Usage.