> ## Documentation Index
> Fetch the complete documentation index at: https://concentrate.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Integrations overview

> Connect Concentrate AI to Claude Code, Claude Desktop, Codex, Cursor, and other OpenAI-compatible tools with a base URL and API key.

Concentrate AI works with the AI coding tools and desktop apps you already use. Because Concentrate is a drop-in, OpenAI-compatible gateway, most integrations are just two values — the base URL and your API key — which unlocks 50+ models across 16+ providers without changing how you work.

## Pick your tool

Match the tool you're using to the guide that walks through the setup.

| If you're using... | Use this guide                                 |
| ------------------ | ---------------------------------------------- |
| Claude Code        | [Claude Code](/docs/integrations/claude-code)       |
| Claude Desktop     | [Claude Desktop](/docs/integrations/claude-desktop) |
| Codex              | [Codex](/docs/integrations/codex)                   |
| Cursor             | [Cursor](/docs/integrations/cursor)                 |

More integrations are on the way. If your tool isn't listed, it can almost certainly connect through the same OpenAI-compatible pattern: point the client at `https://api.concentrate.ai/v1`, use an API key that starts with `sk-cn-v1-`, and pick a model in `provider/model-id` format. See the [Quickstart](/docs/getting-started/quickstart) for a from-scratch setup.

## What every integration has in common

Regardless of which tool you connect, the setup comes down to the same values.

| Setting      | Value                                                                                    |
| ------------ | ---------------------------------------------------------------------------------------- |
| Base URL     | `https://api.concentrate.ai/v1`                                                          |
| Auth header  | `Authorization: Bearer sk-cn-v1-...`                                                     |
| Model format | `provider/model-id` (e.g. `anthropic/claude-haiku-4-5`) or bare slug (`auto`, `gpt-5.4`) |

## What you get

* **One key for every model.** Access 50+ models across 16+ providers through a single API key, with no per-provider accounts to manage.
* **Built-in observability.** Usage, spend, latency, providers, models, and cache hits across your whole org, with no third-party integration.
* **Team-scale spend management.** Budgets at the organization, team, developer, and key level.
* **Strategy-driven auto routing.** Use `model: "auto"` with explicit optimization for cost, latency, or performance. See [Auto Routing](/docs/api-reference/endpoint/auto-routing).

## Feedback

If a tool didn't connect cleanly, email [support@concentrate.ai](mailto:support@concentrate.ai). We use integration friction reports to prioritize compatibility fixes.