Ai Inference as a Service
Claim your API key and run Ai/ML models as a cost-efficient serverless API endpoint.
01. Select Ai/ML Model
02. Select Server Type
03. Call API Endpoint
curl
https://api.ailayer.ai/api/ailayer/v1/
chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer TokenFromAiLayer" \
-d '{
"model": "Llama-2-70b",
"messages": [{"role": "user",
"content": "Hello!"}],
"max_tokens": 500,
"temperature": 0.05
}'04. Run Ai/ML Models