Chat Completions

Non-Streaming Request

curl https://cavos.org/api/v1/chat/completions \
  -H "Authorization: Bearer sk_live_abc123..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Response

{
  "id": "gen-abc123",
  "object": "chat.completion",
  "model": "openai/gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33
  }
}

Streaming Request

Add "stream": true to receive Server-Sent Events (SSE):

curl https://cavos.org/api/v1/chat/completions \
  -H "Authorization: Bearer sk_live_abc123..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

SSE Stream Format

data: {"choices":[{"delta":{"content":"Hello"},"index":0}]}

data: {"choices":[{"delta":{"content":"!"},"index":0}]}

data: {"choices":[{"delta":{},"finish_reason":"stop","index":0}],"usage":{"prompt_tokens":10,"completion_tokens":5}}

data: [DONE]

Multi-Modal Messages

Send images alongside text:

{
  "model": "openai/gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "What's in this image?"},
        {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
      ]
    }
  ]
}

Parameters

Parameter	Type	Default	Description
model	string	—	Model ID (e.g., openai/gpt-4o-mini)
messages	array	—	Array of message objects
temperature	number	1.0	Randomness (0–2)
max_tokens	number	—	Maximum response tokens
stream	boolean	false	Enable SSE streaming
top_p	number	1.0	Nucleus sampling
stop	string[]	—	Stop sequences

Usage Tracking

Every request tracks token usage and cost. Usage is deducted from your credit balance in real-time. View usage history in the dashboard or via the API.