API Access & Authentication
How to get API access and use authentication
API Access & Authentication
Getting API Access
To access the Koveh API services, you need to obtain an API key through our application process.
Application Process
-
Contact Us: Send an email to
studio@koveh.com
with the following information:- Your name and organization
- Intended use case for the API
- Expected request volume
- Technical requirements
-
Required Information: Include in your email:
- Use Case Description: Detailed explanation of how you plan to use our APIs
- Business Context: What problem you're solving or what you're building
- Expected Traffic: Estimated number of requests per day/month
- Technical Stack: What technologies you're using
- Contact Information: Your email and preferred contact method
-
Review Process: Our team will review your application within 2-3 business days
-
API Key Issuance: Upon approval, you'll receive your API key and access credentials
Usage Guidelines
Important: API keys are confidential and should never be shared publicly or committed to version control.
- Rate Limits: Each service has specific rate limits (see individual service documentation)
- Monitoring: We monitor API usage for abuse and may contact you if unusual patterns are detected
- Support: Technical support is available for approved API users
Authentication
All API requests require authentication using Bearer tokens in the Authorization header:
curl -H "Authorization: Bearer YOUR_API_KEY" \
"https://api.koveh.com/qwen3/chat"
Example Usage
import requests
headers = {
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json"
}
response = requests.post(
"https://api.koveh.com/translation/translate",
headers=headers,
json={
"text": "Hello, world!",
"source_language": "en",
"target_language": "es"
}
)
print(response.json())
Rate Limiting
Each service has its own rate limiting to ensure fair usage:
Service | Rate Limit | Window |
---|---|---|
Translation | 100 requests | per minute |
Qwen3 | 50 requests | per minute |
FastVLM | 30 requests | per minute |
Web Search | 60 requests | per minute |
Tinkoff | 100 requests | per minute |
Speech to Text | 20 requests | per minute |
Rate Limit Headers: API responses include headers showing your current usage:
X-RateLimit-Limit
: Maximum requests per windowX-RateLimit-Remaining
: Remaining requests in current windowX-RateLimit-Reset
: Time when the rate limit resets
Error Handling
When rate limits are exceeded or authentication fails, APIs return appropriate HTTP status codes:
{
"error": "Rate limit exceeded",
"status_code": 429,
"retry_after": 60,
"timestamp": "2025-08-30T09:19:31.245295"
}
Best Practices
- Store API Keys Securely: Use environment variables or secure key management
- Implement Retry Logic: Handle rate limits and temporary failures gracefully
- Monitor Usage: Track your API usage to stay within limits
- Cache Responses: Cache responses when appropriate to reduce API calls
- Use HTTPS: Always use HTTPS for API requests
Support & Contact
- Technical Support:
studio@koveh.com
- API Status: Check individual service health endpoints
- Documentation: This documentation site for detailed API references
- Community: GitHub issues for bug reports and feature requests
Need Help?: If you encounter issues or need assistance, don't hesitate to reach out to our team at studio@koveh.com
.