Connect in a minute.

After creating an API key in the Dashboard, set it as an environment variable and make your first request:

curl https://api.voltapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $VOLT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Ahoj!"}]
  }'

Every request needs an Authorization: Bearer `YOUR_API_KEY` header. Keys are generated in the Dashboard and can be scoped to specific projects or models.

For the OpenAI SDK just rewrite baseURL to https://api.voltapi.ai/v1 and use the VoltAPI key. No other code changes.

import OpenAI from "openai";

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

const r = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hello" }]
});

Anthropic SDK works identically through the OpenAI-compatible endpoint. Claude 4 models are available under their native IDs (claude-opus-4, claude-sonnet-4, claude-haiku-4).

VoltAPI returns standard HTTP codes: 401 (invalid key), 402 (quota exhausted), 429 (rate limit), 503 (model temporarily unavailable — we re-route automatically).