# LowRouter > LowRouter is one gateway to many LLM providers and models, compatible with the OpenAI API. Top up credits once, then choose which provider, model, and region handles your requests — and change that choice whenever you like, across 40+ regions through a single endpoint. Most AI gateways hide which provider handled your request. LowRouter does the opposite: every response carries `lowrouter_metadata` revealing the upstream provider, region, grid carbon intensity, and gCO₂eq emitted — and your dashboard breaks down the cost of every call. You choose the provider, model, and region, name just the model with `auto//` and let LowRouter pick the greenest eligible route for it (preferring EU-sovereign providers in EU/EEA regions, and modeled from annual grid averages, not live grid data), or point your code at an alias and repoint it later without any code change. Custom auto-routing policies (like a per-key carbon budget) are coming soon. Operated by Carbonifer SAS (Nantes, France). OpenAI-compatible, so you can switch back any time with no proprietary protocol. One entry point to many providers across 40+ regions, and one bill instead of one per provider. Grid carbon data: Ember Climate country averages (CC-BY 4.0), refined by regional grid operators (PJM, CAISO, ERCOT, BPA, EirGrid, RTE, National Grid ESO, Hydro-Québec, AEMO) where they publish finer permissively-licensed data. Energy modeling via EcoLogits. ## Core - [Landing page](/): Product overview and positioning - [Models catalog](/models): Full list of supported models with per-token carbon estimates - [Providers](/providers): Upstream providers across 40+ regions, filterable by EU sovereignty and carbon - [Documentation](/docs): Integration guide, routing, billing, and sustainability reference - [Help and support](/help): Every support channel — documentation, Discord community, email, and live chat - [FAQ (markdown)](/faq.md): Plain-text FAQ for LLM retrieval - [Full documentation (single file)](/llms-full.txt): Every docs page plus the API reference, concatenated for LLM ingestion ## Philosophy Why LowRouter exists, what it stands for, and where it draws its lines. - [Why LowRouter exists](/docs/philosophy/why-lowrouter.md): The problem we set out to solve, what we built, and what we deliberately left out. - [Sustainability-first](/docs/philosophy/sustainability-first.md): What we measure, what we don't, and how we keep the platform itself within budget. - [Sovereignty and transparency](/docs/philosophy/sovereignty-and-transparency.md): Where we run, what we expose, and how to verify it. - [Principles in practice](/docs/philosophy/principles-in-practice.md): How the principles above map to concrete choices in the product. ## Getting started Set up an account, create an API key, send your first completion, and learn the dashboard in fifteen minutes. - [Create an account](/docs/getting-started/account.md): Sign up, verify your email, and add an initial credit balance so the first request goes through. - [Create your first API key](/docs/getting-started/api-keys.md): How LowRouter API keys work, where to store them, and how to rotate or revoke them. - [Run your first completion](/docs/getting-started/first-completion.md): A single curl request, the response shape, and what each field means. - [Tour the dashboard](/docs/getting-started/dashboard-tour.md): What the four landing widgets show, where to drill in, and how to read the eco panel without overinterpreting it. ## Guides Day-to-day operations: API keys, credits and billing, usage accounting, and the dashboard in depth. - [API key management](/docs/guides/api-keys.md): API keys in depth — scoping, rotation, revocation, and the policies you can attach. - [Credits and billing](/docs/guides/credits-and-billing.md): How credits work, what counts as usage, how invoices are produced, and how pricing maps to upstream providers. - [Usage accounting](/docs/guides/usage-accounting.md): What's recorded per request, how to query and export it, and how long records are kept. - [Dashboard deep-dive](/docs/guides/dashboard-deep-dive.md): Every chart on the dashboard, how it's computed, and how to filter it. - [Pricing and currency conversion](/docs/guides/pricing-and-fx.md): How daily exchange rates and a fixed markup convert non-EUR provider prices to the EUR prices we charge against your balance. - [Errors reference](/docs/guides/errors.md): Every error the gateway returns — status codes, real JSON payloads, and the one-line fix for each. ## Integrations Copy-paste snippets for the OpenAI SDK and the LLM tools developers actually use. - [curl](/docs/integrations/curl.md): The bare HTTP request — useful for debugging, scripting, and confirming the gateway behaviour. - [OpenAI SDK (Python)](/docs/integrations/openai-sdk-python.md): Point the official OpenAI Python SDK at LowRouter by changing two arguments. - [OpenAI SDK (TypeScript)](/docs/integrations/openai-sdk-typescript.md): Use the official openai npm package with LowRouter from Node, Bun, Deno, or the browser (server-only). - [ChatBox](/docs/integrations/chatbox.md): Configure the ChatBox desktop client to talk to LowRouter. - [OpenCode](/docs/integrations/opencode.md): Configure OpenCode to use LowRouter as its model provider. - [Cline](/docs/integrations/cline.md): Configure the Cline VS Code agent to use LowRouter. - [Goose](/docs/integrations/goose.md): Configure the Goose agent to use LowRouter. - [Generic OpenAI-compatible clients](/docs/integrations/openai-compatible.md): The pattern that works for any tool that lets you set a base URL and an API key. ## Models & providers What's routable, how routing decisions are made, and what the per-request metadata means. - [Available models](/docs/models/available.md): How the model catalogue is structured and what to look at on each model card. - [Routing](/docs/models/routing.md): How auto// picks a route, in what order, and how to pin a provider or region. - [Per-request metadata](/docs/models/per-request-metadata.md): The lowrouter_metadata block on every response — every field, what it means, and when it can be missing. - [Model aliases](/docs/models/aliases.md): Name a route once, call it with alias/, and repoint it anytime — no client changes. ## Sustainable AI Methodology, data sources, limits, and practical recommendations for reducing the footprint of inference. - [Methodology](/docs/sustainable-ai/methodology.md): The exact formula, coefficients, and confidence bands behind every energy and carbon number on the platform. - [Data sources](/docs/sustainable-ai/data-sources.md): Where the parameter counts, the energy formula coefficients, and the grid intensities come from. - [Limits and what we don't claim](/docs/sustainable-ai/limits.md): The explicit out-of-scope list — what the eco numbers do not represent. - [Reduce your footprint](/docs/sustainable-ai/reduce-your-footprint.md): Concrete changes to your application that move the dashboard's numbers down. ## Other - [FAQ](/docs/faq.md): Short answers to the questions we get most often about LowRouter. - [About LowRouter](/docs/about.md): Who makes LowRouter, why we built it, and what we care about. ## Legal - [Terms of Service](/terms) - [Privacy Policy](/privacy) - [Cookie Policy](/cookies) - [Acceptable Use Policy](/aup) - [Impressum](/impressum)