Quickstart

Get started with Creed Space in 5 minutes.

1. Get Your API Key

1. Sign up or log in
2. Go to Dashboard → API Keys
3. Click Create New Key
4. Copy and save your key (you won't see it again!)

Important

Store your API key securely. Never commit it to version control or expose it in client-side code.

2. Make Your First Request

Using cURL

curl -X POST "https://api.creed.space/api/v1/safety/evaluate" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input_text": "Hello, how are you?"}'

Using Python

pip install creed-sdk

from creed_sdk import CreedSpace

client = CreedSpace(api_key="YOUR_API_KEY")
result = client.safety.evaluate("Hello, how are you?")

print(f"Risk score: {result.risk_score}")
print(f"Decision: {result.decision}")

Using JavaScript/TypeScript

npm install @creed-space/sdk

import { CreedSpace } from '@creed-space/sdk';

const client = new CreedSpace({ apiKey: 'YOUR_API_KEY' });
const result = await client.safety.evaluate('Hello, how are you?');

console.log(`Risk score: ${result.riskScore}`);
console.log(`Decision: ${result.decision}`);

3. Understand the Response

{
  "status": "success",
  "evaluation": {
    "risk_score": 0.05,
    "decision": "permit",
    "is_blocked": false,
    "matched_rules": [],
    "decision_time_ms": 12.5
  }
}

Field	Type	Description
risk_score	float	0.0 (safe) to 1.0 (dangerous)
decision	string	permit, forbid, divert, or depends
is_blocked	boolean	Whether content should be blocked
matched_rules	array	Safety rules that matched
decision_time_ms	float	Processing time in milliseconds

4. Handle Decisions

result = client.safety.evaluate(user_message)

if result.decision == "permit":
    # Safe to proceed
    process_message(user_message)
elif result.decision == "forbid":
    # Block the content
    return "This message violates our content policy."
elif result.decision == "divert":
    # Route to human review
    queue_for_review(user_message)
else:  # "depends"
    # Requires additional context
    handle_with_context(user_message, result)

Next Steps

• API Reference - Full endpoint documentation
• Error Handling - Handle errors gracefully
• Rate Limits - Understand your limits
• Best Practices - Integration tips

Try the API Playground

Test the API interactively at creed.space/playground.