kral Documentation
Sign in
API

API Quickstart

The kral API is OpenAI-compatible: existing SDKs keep working, you only swap the base URL and the key. Through the same interface you reach every model — Claude, GPT, Gemini, Grok, Mistral, Llama.

1. Create an API key

In the dashboard under API keys, click Create API key. One key per project, with its own spend limits, expiry date, model allowlist and rate limit. Keys start with sk-kral-. The plain-text key is shown once at creation; afterwards only the prefix.

2. Set the base URL

https://api.kral.ai/v1

Authentication is a Bearer token in the Authorization header.

3. First request

cURL

curl https://api.kral.ai/v1/chat/completions \
  -H "Authorization: Bearer $KRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.kral.ai/v1",
    api_key="sk-kral-...",
)

resp = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from "openai";

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

const resp = await client.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);

Models

Pass the model name in the model field. Get the full list with GET /v1/models. More under Endpoints.

Next