curl -s http://localhost:8000/v1/completions -H 'Content-Type: application/json' -d '{"model":"meta-llama/Llama-3.1-8B-Instruct","prompt":"Once upon a time"}'

Uses the completions endpoint for raw prompt continuation without chat formatting, ideal for testing base models or non-chat tasks. The response contains the generated text plus token counts in usage. Chat models usually behave better through /v1/chat/completions, which applies their trained template.