AI API Proxy
API Documentation

Authentication

All API requests require authentication using Bearer tokens. Include your API key in the Authorization header of each request.

curl https://api.aiproxy.io/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

API keys can be obtained from your dashboard. Keys are scoped to specific projects and can have different permission levels.

List Available Models

Retrieves a list of all AI models available through the proxy, including their capabilities, context windows, and pricing information.

Request Parameters

Parameter	Type	Required	Description
provider	string	No	Filter by provider (openai, anthropic, google)
type	string	No	Filter by model type (chat, completion, embedding)

Response

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4-turbo",
      "object": "model",
      "provider": "openai",
      "type": "chat",
      "context_window": 128000,
      "pricing": {
        "input": 0.01,
        "output": 0.03
      }
    }
  ]
}

Create Completion

Generates text completions based on a provided prompt. Supports multiple AI providers with automatic failover and load balancing.

Request Body

Parameter	Type	Required	Description
model	string	Yes	Model ID to use for completion
prompt	string | array	Yes	Input prompt(s) for completion
max_tokens	integer	No	Maximum tokens to generate (default: 16)
temperature	number	No	Sampling temperature 0-2 (default: 1)
provider	string	No	Preferred provider (auto-selected if omitted)

Example Request

curl https://api.aiproxy.io/v1/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4-turbo",
    "prompt": "Explain quantum computing in simple terms",
    "max_tokens": 500,
    "temperature": 0.7
  }'

Response

{
  "id": "cmpl-abc123",
  "object": "text_completion",
  "created": 1699000000,
  "model": "gpt-4-turbo",
  "provider": "openai",
  "choices": [
    {
      "text": "Quantum computing is a revolutionary approach...",
      "index": 0,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 488,
    "total_tokens": 500
  }
}

Create Chat Completion

Creates a chat completion with conversation context. Supports multi-turn conversations, system prompts, and various message roles.

Request Body

Parameter	Type	Required	Description
model	string	Yes	Model ID for chat completion
messages	array	Yes	Array of message objects with role and content
temperature	number	No	Sampling temperature 0-2
stream	boolean	No	Enable streaming responses

Example Request

{
  "model": "claude-3-opus",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is machine learning?"}
  ],
  "temperature": 0.8,
  "stream": false
}

Create Embeddings

Generates vector embeddings for text inputs. Useful for semantic search, clustering, and similarity comparisons.

Request Body

Parameter	Type	Required	Description
model	string	Yes	Embedding model ID (e.g., text-embedding-3-large)
input	string | array	Yes	Text input(s) to embed
dimensions	integer	No	Output dimensions (model-dependent)

curl https://api.aiproxy.io/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-large",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Error Handling

The API uses standard HTTP status codes to indicate errors. Error responses include detailed messages to help diagnose issues.

Error Response Format

{
  "error": {
    "type": "invalid_request_error",
    "code": "invalid_api_key",
    "message": "The API key provided is invalid",
    "param": null
  }
}

Common Error Codes

Code	Type	Description
invalid_api_key	authentication_error	API key is missing or invalid
rate_limit_exceeded	rate_limit_error	Too many requests in time window
model_not_found	invalid_request_error	Specified model does not exist
context_length_exceeded	invalid_request_error	Input exceeds model context window

Rate Limits

Rate limits are applied per API key and vary based on your subscription tier. Rate limit information is included in response headers.

Rate Limit Headers

X-RateLimit-Limit: 1000
X-RateLimit-Remaining: 950
X-RateLimit-Reset: 1699000000