Tired of OpenAI storing your prompts? I built NullLog — private LLM inference with zero data retention. - OpenAI-compatible (change one line) - 7 models including Llama 3.3 70B + DeepSeek R1 - $59/month - Instant API key Try it: https://api.sparsitron.com from openai import OpenAI client = OpenAI( api_key="your-key", base_url="https://api.sparsitron.com/v1" )