Cybersecurity AI API
Integrate SYLink's cybersecurity-specialized language models into your products. OpenAI-compatible — use any existing SDK. EU-hosted, zero data leakage.
pip install openainpm install openaiQuick Start
from openai import OpenAI
client = OpenAI(
api_key="sk-syl-YOUR_KEY",
base_url="https://sylink-ai.fr/api/v1"
)
response = client.chat.completions.create(
model="sylink2-9b",
messages=[
{"role": "system", "content": "You are a cybersecurity analyst."},
{"role": "user", "content": "Analyze CVE-2024-3094 and recommend mitigations."}
]
)
print(response.choices[0].message.content)Models & Pricing
All prices in EUR per 1 million tokens (MTok). Cybersecurity-specialized models trained on threat intelligence, vulnerability analysis, and incident response data.
| Model | Parameters | Context | Input | Output | Best For |
|---|---|---|---|---|---|
| sylink-8b | 8B | 40K | €0.15 | €0.60 | Fast triage, SOC automation |
| sylink-32b | 32B | 40K | €0.50 | €1.50 | Detailed analysis, report generation |
| sylink2-9b | 9B | 256K | €0.15 | €0.60 | Fast triage, long context analysis |
| sylink2-27b | 27B | 256K | €0.40 | €1.20 | Threat hunting, IOC extraction |
| sylink2-80b | 80B | 256K | €1.20 | €3.50 | Expert analysis, compliance audits |
API Reference
POST /v1/chat/completions
Generate a chat completion. Fully compatible with the OpenAI Chat Completions API. If no system message is provided, SYLink's cybersecurity system prompt is injected automatically.
| Parameter | Type | Default | Description |
|---|---|---|---|
| model | string | required | Model ID (see table above) |
| messages | array | required | 1-256 messages with role + content |
| temperature | float | 0.7 | 0-2. Use 0.3-0.5 for analytical tasks. |
| top_p | float | 1.0 | 0-1. Nucleus sampling. |
| max_completion_tokens | integer | model default | 1-32768. Maximum output tokens. |
| stream | boolean | false | Enable SSE streaming. |
| stop | string | string[] | null | Up to 4 stop sequences. |
Request
{
"model": "sylink2-9b",
"messages": [
{"role": "system", "content": "You are a SOC analyst."},
{"role": "user", "content": "Analyze CVE-2024-3094."}
],
"temperature": 0.4,
"max_completion_tokens": 4096,
"stream": false
}Response
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"model": "sylink2-9b",
"choices": [{
"message": {
"role": "assistant",
"content": "## CVE-2024-3094\n..."
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 150,
"completion_tokens": 892,
"total_tokens": 1042
}
}GET /v1/models
List all available models with pricing, context length, and generation metadata.
Error Codes
| HTTP | Type | When |
|---|---|---|
| 400 | invalid_request_error | Malformed request or invalid parameters |
| 401 | authentication_error | Missing, invalid, or revoked API key |
| 402 | billing_error | Insufficient account balance |
| 404 | invalid_request_error | Model not found |
| 429 | rate_limit_error | Rate limit or token quota exceeded |
| 503 | server_error | Model unavailable or server at capacity |
Billing
SYLink uses a prepaid balance system. Each API request deducts the actual token cost (prompt + completion tokens) from your account balance. If your balance is insufficient, the API returns HTTP 402. Monitor your usage in the Developers dashboard.
Rate Limits & Plans
| Plan | Models | API Keys | Rate Limit | Daily Tokens | Monthly Tokens |
|---|---|---|---|---|---|
| Free | V1 (8B, 32B) | 1 | 20 RPM | 100K | - |
| Pro (€39/mo) | V2 (9B, 27B, 80B) | 5 | 60 RPM | Unlimited | 10M |
| Enterprise | All models | 25+ | 120+ RPM | Unlimited | Unlimited |
All plan upgrades are handled by our commercial team. Contact contact@sylink.fr