API Key Management

Manage API keys for secure access to your Prediction Guard platform.

Creating API Keys

Basic API Key Creation

1. Navigate to API Keys in the admin panel
2. Click “Create API Key”
3. Enter key details:
   • Name (for identification)
   • Key Type (Evaluation, Ultimate, Enterprise)
   • Expiration date (optional)
4. Set rate limits:
   • Requests per second
   • Burst capacity
5. Configure usage quota:
   • Quota amount
   • Quota period (Day, Week, Month)
6. Click “Create API Key” to generate the key

API Key Settings

Key Configuration

• Name: Descriptive name for the API key
• Key Type: Evaluation, Ultimate, or Enterprise
• Expiration: Set expiration date or make it permanent
• Organization: Automatically assigned to your organization
• Cluster: Automatically assigned to your cluster

Rate Limits

• Requests Per Second: Maximum API calls per second
• Burst: Maximum burst capacity for traffic spikes
• Unlimited Requests: Toggle for unlimited rate limits
• Unlimited Burst: Toggle for unlimited burst capacity

Usage Quota

• Quota Amount: Total usage limit (e.g., 10,000 requests)
• Quota Period: Time period (Day, Week, Month)
• Unlimited Quota: Toggle for unlimited usage

Managing API Keys

Basic Operations

• View Keys: See all your API keys and their status
• Edit Settings: Modify rate limits and quotas
• Regenerate: Create new key with same settings
• Revoke: Disable key access immediately
• Delete: Permanently remove the key

Security Best Practices

• Store securely: Use environment variables or secure vaults
• Rotate regularly: Change keys periodically for security
• Monitor usage: Track API key activity and usage patterns
• Revoke unused: Remove keys that are no longer needed

Integration Examples

Environment Variables

$
export PREDICTIONGUARD_API_KEY="your-api-key-here"
>
export PREDICTIONGUARD_URL="https://your-domain.com"

Python SDK

1
import os
2
from predictionguard import PredictionGuard
3
4
# Set API key as environment variable
5
os.environ["PREDICTIONGUARD_API_KEY"] = "your-api-key-here"
6
7
# Create client
8
client = PredictionGuard()
9
10
# Use the API
11
result = client.chat.completions.create(
12
    model="Hermes-3-Llama-3.1-70B",
13
    messages=[
14
        {
15
            "role": "user",
16
            "content": "Hello, world!"
17
        }
18
    ],
19
    max_completion_tokens=100
20
)

cURL Example

$
curl -X POST "https://your-domain.com/chat/completions" \
>
  -H "Authorization: Bearer your-api-key-here" \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "model": "Hermes-3-Llama-3.1-70B",
>
    "messages": [
>
      {
>
        "role": "user",
>
        "content": "Hello, world!"
>
      }
>
    ],
>
    "max_completion_tokens": 100
>
  }'

Complete documentation coming soon - Advanced API key management features and integration guides are being developed.