.svg){kind=small}
API Endpoints
Ultrasafe provides a single, unified API endpoint for chat completions, designed specifically for UltraSafe models with their specialized capabilities.
API Endpoint
Available Models
- ultrasafe/usf-mini - Base UltraSafe model for general use
- ultrasafe/usf-healthcare - Healthcare specialist model
- ultrasafe/usf-finance - Finance and economics expert model
- ultrasafe/usf-code - Programming and development expert model
- ultrasafe/usf-psychology - Psychology expert model
UltraSafe models offer specialized capabilities optimized for specific domains. See the UltraSafe model documentation for detailed information about each model.
Request Format
All requests to the UltraSafe API follow a simple, consistent format that's compatible with OpenAI client libraries.
1POST /api/v2/chat/completions
2Content-Type: application/json
3Authorization: Bearer YOUR_API_KEY
4
5{
6 "model": "ultrasafe/usf-mini",
7 "messages": [
8 {"role": "system", "content": "You are a helpful assistant."},
9 {"role": "user", "content": "Hello, who are you?"}
10 ],
11 "temperature": 0.7,
12 "max_tokens": 500,
13 "stream": false
14}Response Format
The API returns responses in a consistent format, similar to the OpenAI API format that many developers are already familiar with.
1{
2 "model": "ultrasafe/usf-mini",
3 "id": "ultrasafe-id_yNwd8EyBzJJO1W2nV",
4 "conversation_id": null,
5 "choices": [
6 {
7 "index": 0,
8 "finish_reason": "stop",
9 "message": {
10 "role": "assistant",
11 "content": "Hello! I'm functioning optimally today, thank you for asking. How can I assist you?"
12 }
13 }
14 ],
15 "token_metrics": {
16 "input_tokens": 125,
17 "output_tokens": 21,
18 "total_tokens": 146
19 }
20}For more details on the response format and how to parse it, see the Response Format documentation.
Next Steps
Continue exploring the Ultrasafe API by learning about authentication and making your first API request.