Quickstart

Get your first LLM response through Cynos in under 5 minutes.

1. Get a virtual key

Create a virtual key through the Cynos management console.

The virtual key starts with sk-cy-. Save it - the full secret is shown only once.

2. Make your first request

Send a chat completion request using your virtual key:

curl https://api.cynos.averlon.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-cy-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {"role": "user", "content": "Explain Log4Shell (CVE-2021-44228) in one paragraph"}
    ]
  }'

Response:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1724000000,
  "model": "gpt-4o-2024-08-06",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Log4Shell (CVE-2021-44228) is a severe software security flaw in Apache Log4j, a widely used Java tool that records system events. The bug occurs because the tool evaluates special text strings using a feature that fetches data from external sources. An attacker can type a malicious command into an input field—like a search box—that gets saved in the system logs. When Log4j processes this text, it contacts an outside server controlled by the hacker, downloads harmful files, and runs them. This grants the attacker remote access to take complete control of the affected computer or server"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 8,
    "total_tokens": 22
  }
}

3. Try a different provider

Switch providers by changing the model prefix - no configuration needed:

# Anthropic
curl https://api.cynos.averlon.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-cy-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-20250514",
    "messages": [
      {"role": "user", "content": "Draft a remediation plan for Log4Shell (CVE-2021-44228)"}
    ]
  }'

# Google Gemini
curl https://api.cynos.averlon.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-cy-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini/gemini-2.5-pro",
    "messages": [
      {"role": "user", "content": "Draft a remediation plan for Log4Shell (CVE-2021-44228)"}
    ]
  }'

4. Use with the OpenAI SDK

Since Cynos is OpenAI-compatible, point any OpenAI SDK at it:

Python:

from openai import OpenAI

client = OpenAI(
    api_key="sk-cy-your-api-key",
    base_url="https://api.cynos.averlon.ai/v1"
)

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello, Cynos!"}]
)

print(response.choices[0].message.content)

TypeScript:

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-cy-your-api-key',
  baseURL: 'https://api.cynos.averlon.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [{ role: 'user', content: 'Hello, Cynos!' }],
});

console.log(response.choices[0].message.content);

5. Enable intelligent features (optional)

Let Cynos pick the best model

Omit the model field or use the task routing header to let Cynos classify your prompt and route to the optimal model:

curl https://api.cynos.averlon.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-cy-your-api-key" \
  -H "Content-Type: application/json" \
  -H "x-cy-eh-task-route: on" \
  -d '{
    "messages": [
      {"role": "user", "content": "Draft a remediation plan for Log4Shell (CVE-2021-44228)"}
    ]
  }'

Enable quality refinement

Add judge_effort to have responses evaluated and refined:

curl https://api.cynos.averlon.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-cy-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "judge_effort": "high",
    "messages": [
      {"role": "user", "content": "Write a detailed security analysis of CVE-2024-3094"}
    ]
  }'

What's next

Authentication — Understand virtual keys and auth options
Task Routing — How intelligent model selection works
Iterative Self Refinement — Configure response refinement