API Reference

Complete reference for the 2389 API. Our endpoints are OpenAI-compatible, so you can use existing OpenAI client libraries.

Base URL

https://id.2389.ai/v1

Authentication

All API requests require an API key passed in the Authorization header:

Authorization: Bearer sk-2389-YOUR_API_KEY

Endpoints

List Models

GET /v1/models

Returns a list of available models.

curl https://id.2389.ai/v1/models \
  -H "Authorization: Bearer sk-2389-YOUR_API_KEY"

Chat Completions

POST /v1/chat/completions

Creates a chat completion for the given messages.

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID to use (see available models below)
`messages`	array	Yes	Array of message objects with role and content
`stream`	boolean	No	Enable streaming responses (default: `false`)
`temperature`	number	No	Sampling temperature (0-2)
`max_tokens`	integer	No	Maximum tokens in the response

Message Object

Field	Type	Description
`role`	string	One of: `system`, `user`, `assistant`
`content`	string	The message content

Example Request

curl -X POST https://id.2389.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-2389-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "temperature": 0.7
  }'

Example Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "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
  }
}

Available Models

OpenAI Models

Model ID	Description
`gpt-4o`	Most capable GPT-4 model
`gpt-4o-mini`	Affordable, fast GPT-4 model
`gpt-4-turbo`	GPT-4 Turbo with vision capabilities
`gpt-4`	Original GPT-4 model
`gpt-3.5-turbo`	Fast and cost-effective
`o1`	Reasoning model for complex tasks
`o1-mini`	Smaller, faster reasoning model

Anthropic Models

Model ID	Description
`claude-opus-4-5-20250514`	Most capable Claude model
`claude-sonnet-4-5-20250514`	Balanced performance and speed
`claude-sonnet-4-20250514`	Latest Sonnet model
`claude-3-5-sonnet-20241022`	Claude 3.5 Sonnet
`claude-3-5-haiku-20241022`	Fast and efficient
`claude-3-opus-20240229`	Claude 3 Opus
`claude-3-haiku-20240307`	Claude 3 Haiku

Streaming

Set stream: true to receive responses as Server-Sent Events (SSE). Each event contains a delta of the response.

curl -X POST https://id.2389.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-2389-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Rate Limits

API requests are rate limited to 60 requests per minute per API key.

Rate limit headers are included in all responses:

Header	Description
`X-RateLimit-Limit`	Maximum requests per window
`X-RateLimit-Remaining`	Requests remaining in current window
`X-RateLimit-Reset`	Unix timestamp when the window resets

Error Responses

Errors follow the OpenAI error format:

{
  "error": {
    "message": "Invalid API key",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

Common Error Codes

HTTP Status	Error Code	Description
401	`invalid_api_key`	Missing or invalid API key
400	`invalid_request_error`	Malformed request body
404	`model_not_found`	Requested model does not exist
429	`rate_limit_exceeded`	Too many requests
500	`internal_error`	Server error