Language Models API
Build smarter applications using AI with our powerful and secure API.
Get started quickly with our developer-friendly endpoints and robust security features.
Getting Started
API Key Authentication
-
1. Get your API key from the Account Settings
-
2. Set the Authorization header: Bearer YOUR_API_KEY
-
3. Make your first request to /api/v1/complete
curl -X POST \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"prompt":"Once upon a time","max_tokens":50}' \ https://api.llm.org/v1/complete
Available Endpoints
Text Generation
Generate text completions using our large language models
POST /api/v1/complete
- JSON API
- Bearer Auth
Embedding Generation
Create vector embeddings of text for similarity searches
POST /api/v1/embed
- JSON API
- Bearer Auth
Batch Processing
Process multiple requests in a single batch for efficiency
POST /api/v1/batch
- JSON API
- Bearer Auth
Request Examples
Sample Request
POST /api/v1/complete
{"Authorization": "Bearer your_api_key", "Content-Type": "application/json"}
{"prompt": "Explain quantum computing in simple terms", "max_tokens": 100, "temperature": 0.7}
- Prompt: User query or instruction
- max_tokens: Maximum tokens in response
- Temperature: Response creativity (0.1-2.0)
Sample Response
Status: 200 OK
{"text": "Quantum computing uses qubits that can exist in multiple states simultaneously...",
"usage": {"prompt_tokens": 7, "completion_tokens": 63}}
Headers