Documentation

Getting Started

Four steps to get started:

1. Create an account — Sign up at manage.callaiapi.com

2. Add balance — Top up via USDT or Alipay/WeChat in the "Top Up" page

3. Create an API Key — Go to "API Keys" and click "New"

4. Make your first request — Just swap the base_url to our gateway

# Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    api_key="csk-your-api-key",
    base_url="https://claude.callaiapi.com/v1",
)

response = client.chat.completions.create(
    model="claude-sonnet-4-20250514",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

// Node.js (OpenAI SDK)
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "csk-your-api-key",
  baseURL: "https://claude.callaiapi.com/v1",
});

const response = await client.chat.completions.create({
  model: "claude-sonnet-4-20250514",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

# cURL
curl https://openai.callaiapi.com/v1/chat/completions \
  -H "Authorization: Bearer csk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

---

CallStack AI Gateway is fully compatible with the OpenAI API specification. Integration requires only a base URL change — no code modifications needed.

Endpoint Configuration

Each model provider has a dedicated gateway endpoint:

Authentication

All requests require an API key in the Authorization header:

Authorization: Bearer csk-your-api-key

API keys can be managed through the admin dashboard or via the management API.

Compatibility

The gateway accepts requests in standard OpenAI API format. Any SDK, framework, or tool that supports OpenAI can be used directly:

Available Models

For the full model catalog, see Supported Models.

API Reference

Chat Completions

POST /v1/chat/completions

Standard OpenAI Chat Completions format. Supports streaming, function calling, and multimodal inputs (model-dependent).

Models

GET /v1/models

Returns the list of models available on the specified gateway endpoint.

Embeddings

POST /v1/embeddings

Generate vector embeddings using supported embedding models.

Rate Limits

Error Codes

Support

For technical assistance, contact our engineering team:

• Email: [email protected]
• Enterprise: Dedicated Slack channel (Enterprise plan)