Quickstart

Send your first request to Radium in four steps

Quickstart

1. Create an account

Go to deploy.radium.cloud and sign up.

2. Create an API key

Navigate to API Keys in the dashboard. Click Create key, copy the value and export it in your terminal.

export RADIUM_API_KEY="YOUR_RADIUM_API_KEY"

3. Send a request

cURL

curl -X POST https://api.radium.cloud/v1/chat/completions \\
  -H "Authorization: Bearer $RADIUM_API_KEY" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "clarke-1.0",
    "messages": [{"role": "user", "content": "Explain rate limiting in 3 sentences."}]
  }'

4. Read the response

A Chat Completions response looks like this:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1699999999,
  "model": "clarke-1.0",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Rate limiting controls how many requests a client can make..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 19,
    "completion_tokens": 45,
    "total_tokens": 64
  }
}

Same request in Anthropic format

cURL

curl -X POST https://api.radium.cloud/v1/messages \\
  -H "x-api-key: $RADIUM_API_KEY" \\
  -H "anthropic-version: 2023-06-01" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "clarke-1.0",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Explain rate limiting in 3 sentences."}]
  }'

Anatomy of a request

1. Base URL: https://api.radium.cloud/v1 for OpenAI format, https://api.radium.cloud for Anthropic format.
2. API key: Passed as Authorization: Bearer for OpenAI, or x-api-key for Anthropic.
3. Model string: hal-1.0, clarke-1.0 or tycho-1.0.
4. Messages: Same array of {role, content} objects you already use.

Next steps

Models overview

Compare tiers and pick the right model

Authentication

Keys, rotation and security

From OpenAI

Parameter compatibility guide

From Anthropic

Messages API migration