Loading
LLMs
Operate large language models responsibly. Learn prompting, fine-tuning, distillation, evaluation, safety, latency, cost control, caching, and observability. Build pipelines that turn models into dependable products.
214 posts34 contributors
+ Follow3 developers follow this
Ask a questionForums in LLMs
How do you reduce your LLM costs?
Hi 👋 This is a question for people whose main product involves calling APIs of Large language models like OpenAI etc. What are you doing to keep the costs of using the model low? Also, are you changing or improving the user's input before sending it to the model? Thanks in advance!
