> ## Documentation Index > Fetch the complete documentation index at: https://docs.routeway.ai/llms.txt > Use this file to discover all available pages before exploring further. # Overview > The fundamental building blocks behind every Routeway API call. Before diving into advanced guides, it helps to understand a handful of concepts that underpin every request you make through Routeway. This section covers them in depth — read it once and the rest of the docs will make much more sense. ## What's in this section ### Chat Completions How the `messages` array works, what `system`, `user`, and `assistant` roles do, and how to build multi-turn conversations correctly. What tokens are, how context windows limit request size, and how to manage long conversations without hitting the limit or running up costs. How Routeway routes a request to the right upstream provider, how to pick the right model for your use case, and how to pin versions for stable production behavior. The full anatomy of a chat completion request and response — every key parameter, what `finish_reason` values mean, and how errors are shaped. ### Responses The full anatomy of a Responses API request and response — input formats, output structure, and key parameters. Use `previous_response_id` to build stateful conversations without resending full message history. Leverage web search, file search, and code interpreter without defining custom function schemas. ### Image Generation Turn a text prompt into an image. Covers models, sizes, quality presets, response formats, and saving images locally. Modify an existing image with a prompt and optional mask. Covers inpainting, multi-image edits, and advanced parameters like `strength` and `guidance_scale`. *** ## Where to go next Once you're comfortable with these fundamentals, the [Guides](/guides/chat-completions/overview) show you how to use streaming, tool calling, structured outputs, reasoning models, multimodal inputs, and caching — all of which build directly on what's covered here.