> ## Documentation Index > Fetch the complete documentation index at: https://docs.inquantum.ai/llms.txt > Use this file to discover all available pages before exploring further. # Planck guides > Practical guides for choosing models, making gateway requests, prompting effectively, and building production LLM applications. Use these guides when you want to complete a task end to end. API reference pages document individual endpoints; guides connect model discovery, request configuration, response handling, and production concerns. ## Start with the API Authenticate, filter the model catalog, call a model, and read the response. Proxy streaming responses through a Next.js or FastAPI backend without exposing your key. ## Prompting Write clear prompts, provide useful context, and choose reliable output constraints. Separate task instructions from API-level reasoning controls and choose an appropriate effort. ## Common application patterns Return schema-constrained data that your application can validate. Let a model request application-defined functions safely. Find endpoints that accept images or other input modalities. Configure thinking effort with OpenAI-compatible or Anthropic-compatible requests. Lock a provider, configure BYOK, or allow automatic routing and fallbacks. Handle validation, authentication, provider, and streaming failures.