Cybernethicc FREYA

FREYA is an AI inference API that provides access to multiple model tiers through a single, OpenAI-compatible endpoint. Use it to add AI capabilities to your applications with simple HTTP requests.

Getting Started

Set up your account and make your first AI request.

Authentication

All inference requests are authenticated with your FREYA API key. Include it as a Bearer token in the Authorization header.

Authorization: Bearer FREYA-YOUR_API_KEY

API keys are prefixed with FREYA-. Requests with missing, invalid, or revoked keys receive a 401 Unauthorized response.

Model Tiers

FREYA offers three model tiers. Choose the right tier based on your task complexity and budget requirements.

List Models

Retrieve the list of available models. No authentication required.

GET https://freya.cybernethicc.com/v1/models

Chat Completions

Create a chat completion by sending a conversation history to the model. The API follows the OpenAI chat completions format.

Request Body

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1711680000,
  "model": "freya-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses quantum bits (qubits) that can exist in multiple states simultaneously..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 32,
    "completion_tokens": 128,
    "total_tokens": 160
  }
}

Streaming

Set stream: true to receive tokens as they are generated via server-sent events (SSE). Each event contains a JSON chunk with a delta field.

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1711680000,"model":"freya-pro","choices":[{"index":0,"delta":{"role":"assistant","content":"Quantum"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1711680000,"model":"freya-pro","choices":[{"index":0,"delta":{"content":" computing"},"finish_reason":null}]}

data: [DONE]

The stream ends with a data: [DONE] message. The OpenAI Python and Node.js SDKs handle streaming automatically.

Code Examples

Basic Request

curl https://freya.cybernethicc.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer FREYA-YOUR_API_KEY" \
  -d '{
    "model": "freya-pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

The Python and Node.js examples use the official openai SDK. Install with pip install openai or npm install openai. The Go example uses github.com/openai/openai-go.

Streaming Example

from openai import OpenAI

client = OpenAI(
    api_key="FREYA-YOUR_API_KEY",
    base_url="https://freya.cybernethicc.com/v1",
)

stream = client.chat.completions.create(
    model="freya-pro",
    messages=[
        {"role": "user", "content": "Write a short poem about the ocean."},
    ],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Rate Limits

Rate limits are applied per API key. The default limit is 60 requests per minute. When exceeded, the API returns a 429 Too Many Requests response.

Need higher limits? Contact support or upgrade to GPU Dedicated.

Pricing

FREYA uses token-based pricing, billed per 1 million tokens. Usage is deducted from your billing account balance in real time after each request.

GPU Dedicated

Error Handling

The API returns standard HTTP status codes and a JSON error body.

Error Response Format

{
  "error": {
    "message": "Invalid or revoked API key",
    "type": "authentication_error"
  }
}