> ## 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 Features > Explore Planck's model gateway, reliability controls, observability, prompt management, and integrations Use this map to find the part of Planck that matches the problem you are solving. If you have not sent a request yet, begin with the [quickstart](/getting-started/quick-start). ## Models and inference Call supported models through OpenAI-compatible or Anthropic-compatible APIs. Generate text with familiar request and response formats. Find models by operation, modality, parameter, and provider endpoint. Choose a provider or let Planck route across compatible endpoints. Let models request application-defined functions. Constrain model output to a schema your application can validate. Work with embeddings, reranking, images, video, audio, and files. ## Reliability and controls Apply production behavior without rebuilding each provider integration. Understand eligible retries, provider failures, and fallback behavior. Reuse eligible gateway responses to reduce latency and cost. Reuse provider-side prompt context on supported endpoints. Control request, cost, or property-based usage. Detect prompt attacks inline and handle blocked requests. Configure supported request-level gateway behavior. ## Observability Connect model activity to the users, sessions, and application context that produced it. Inspect inputs, outputs, cost, latency, errors, and provider details. Add consistent metadata for filtering and analysis. Group related calls into conversations and agent workflows. Attach automated evaluations and end-user feedback to requests. Curate reusable request sets for evaluation and export. Deliver completed request events to your systems. ## Prompt management Version, assemble, and deploy prompts independently from application releases. Create reusable, versioned prompt definitions. Select and render managed prompts in gateway requests. Understand templates, variables, messages, and runtime parameters. ## Integrations Use Planck as the request path, add it to an existing provider integration, or record non-model steps in a larger trace. Compare gateway, automatic logging, manual logging, and custom traces. Connect Codex, LangChain, Semantic Kernel, Vercel AI SDK, and more. Record tools, retrieval, and application-specific operations. ## Keep exploring Follow end-to-end application and prompting walkthroughs. Inspect gateway and platform endpoints in detail.