Invite Only Access

API Documentation

Build with Rapshee's hosted LLMs. Our API is OpenAI-compatible and works with any standard client.

Self-Hosted Compatible

Works with any OpenAI-compatible client or SDK.

Low Latency

Response times under 200ms for most requests.

Simple Integration

Just a URL and API key. No complex setup.

Authentication

All API requests require authentication using an API key. Include your key in the Authorization header.

Connection Details

Base URLhttps://api.rapshee.com/v1

Authorization HeaderBearer YOUR_API_KEY

Content-Typeapplication/json

headers.txt

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Chat Completions

Generate conversational responses. The API follows the OpenAI chat completions format.

POST/v1/chat/completions

Request

request.js

const response = await fetch('https://api.rapshee.com/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer YOUR_API_KEY'
  },
  body: JSON.stringify({
    model: 'rapshee-1',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'What is artificial intelligence?' }
    ],
    temperature: 0.7,
    max_tokens: 1000
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

Response

response.json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1699000000,
  "model": "rapshee-1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Artificial intelligence (AI) refers to..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  }
}

Parameters

Parameter	Type	Description
`model`	string	Model ID to use (required)
`messages`	array	Array of message objects (required)
`temperature`	number	Sampling temperature, 0-2 (default: 1)
`max_tokens`	integer	Maximum tokens to generate
`stream`	boolean	Enable streaming responses (default: false)

Models

Available models for use with the API.

rapshee-1

Our flagship model. Best for general tasks, conversations, and complex reasoning.

Context:128K

Speed:Fast

rapshee-1-mini

Lightweight model optimized for speed. Great for simple tasks and high-throughput applications.

Context:32K

Speed:Fastest

Rate Limits

API rate limits depend on your access tier.

Tier	Requests/min	Tokens/min
Developer	60	40,000
Pro	300	200,000
Enterprise	Custom	Custom

Error Handling

The API uses standard HTTP status codes and returns detailed error messages.

Code	Description
`400`	Bad Request - Invalid parameters
`401`	Unauthorized - Invalid or missing API key
`429`	Too Many Requests - Rate limit exceeded
`500`	Internal Server Error

error-response.json

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

Rapshee Projects

Explore other projects built with Rapshee.

Rapshee Chat

Conversational AI assistant. Chat with Rapshee in your browser.

Live

Rapshee Vision

Coming Soon

Multimodal AI for image understanding and generation.

In Development

Rapshee Code

Coming Soon

AI-powered code assistant for developers.

In Development

Rapshee Translate

Coming Soon

Real-time translation across 100+ languages.

In Development

Ready to build?

Request API access to start building with Rapshee. Tell us about your project and get an invite to test our hosted LLMs.

Request Access Back to Home