API Reference

Authentication

The AI Platform API uses API keys for authentication. Include your API key in the Authorization header of all requests.

curl https://api.aiplatform.com/v2/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json"

Rate Limits

Rate limits vary by plan tier. Limits are applied per API key and reset every minute.

/v2/completions

Creates a completion for the provided prompt and parameters. Returns generated text based on your input.

Request Body

Example Request

import aiplatform

client = aiplatform.Client(api_key="YOUR_API_KEY")

response = client.completions.create(
    model="aip-4-turbo",
    prompt="Explain quantum computing in simple terms:",
    max_tokens=500,
    temperature=0.7
)

print(response.text)

Example Response

{
  "id": "cmpl-abc123",
  "object": "text_completion",
  "created": 1704067200,
  "model": "aip-4-turbo",
  "choices": [{
    "text": "Quantum computing uses quantum mechanics...",
    "index": 0,
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 156,
    "total_tokens": 164
  }
}

/v2/embeddings

Creates an embedding vector representing the input text. Use for semantic search, clustering, and recommendations.

response = client.embeddings.create(
    model="aip-embed-v2",
    input="The quick brown fox jumps over the lazy dog"
)

embedding = response.data[0].embedding
# Returns 1536-dimensional vector

/v2/models

Lists all available models and their capabilities.

curl https://api.aiplatform.com/v2/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Error Handling

The API uses standard HTTP response codes to indicate success or failure.