# Integrations

Most AI-enabled editors, agents, chat apps and frameworks let you bring your own provider. Claudech serves both the OpenAI Chat Completions format and the Anthropic Messages format with standard `sk-` keys, so these tools work without plugins or proxies. Each tool below has its own step-by-step guide.

Every tool needs the same three values:

| Value | OpenAI-format tools | Anthropic-format tools |
| --- | --- | --- |
| Base URL | `https://api.claudech.com/v1` | `https://api.claudech.com` |
| API key | `sk-...` from [API keys](https://claudech.com/api-keys) | same key |
| Model | A slug from [Models](https://claudech.com/docs/models), e.g. `claude-opus-5-5` | same slugs |

> **Which format does my tool use?**
>
> If the setting is called "OpenAI API key" or "OpenAI-compatible", use the first column. If it is called "Anthropic API key" or asks for an `ANTHROPIC_BASE_URL`, use the second. Some tools offer both; either works and is billed identically.

## Coding tools

| Tool | What it is | Guide |
| --- | --- | --- |
| Cursor | AI code editor | [Cursor setup](https://claudech.com/docs/integrations/cursor) |
| Claude Code | Terminal coding agent (Anthropic format) | [Claude Code setup](https://claudech.com/docs/integrations/claude-code) |
| Cline | VS Code agent extension | [Cline setup](https://claudech.com/docs/integrations/cline) |
| Roo Code | VS Code agent extension | [Roo Code setup](https://claudech.com/docs/integrations/roo-code) |
| Kilo Code | VS Code and JetBrains agent extension | [Kilo Code setup](https://claudech.com/docs/integrations/kilo-code) |
| Continue | VS Code and JetBrains assistant | [Continue setup](https://claudech.com/docs/integrations/continue) |
| Aider | Terminal pair programmer | [Aider setup](https://claudech.com/docs/integrations/aider) |
| Zed | Code editor with an agent panel | [Zed setup](https://claudech.com/docs/integrations/zed) |
| OpenCode | Terminal coding agent | [OpenCode setup](https://claudech.com/docs/integrations/opencode) |
| OpenHands | Autonomous coding agent | [OpenHands setup](https://claudech.com/docs/integrations/openhands) |

## Chat apps

| Tool | What it is | Guide |
| --- | --- | --- |
| Open WebUI | Self-hosted chat interface | [Open WebUI setup](https://claudech.com/docs/integrations/open-webui) |
| LibreChat | Self-hosted multi-provider chat | [LibreChat setup](https://claudech.com/docs/integrations/librechat) |
| TypingMind | Browser chat front-end | [TypingMind setup](https://claudech.com/docs/integrations/typingmind) |
| Chatbox | Desktop and mobile chat app | [Chatbox setup](https://claudech.com/docs/integrations/chatbox) |
| SillyTavern | Character and story chat front-end | [SillyTavern setup](https://claudech.com/docs/integrations/sillytavern) |

## Frameworks and automation

| Tool | What it is | Guide |
| --- | --- | --- |
| LangChain | Python and JavaScript LLM framework | [LangChain setup](https://claudech.com/docs/integrations/langchain) |
| Vercel AI SDK | TypeScript AI toolkit | [Vercel AI SDK setup](https://claudech.com/docs/integrations/vercel-ai-sdk) |
| LlamaIndex | Data and agent framework | [LlamaIndex setup](https://claudech.com/docs/integrations/llamaindex) |
| LiteLLM | Multi-provider SDK and proxy | [LiteLLM setup](https://claudech.com/docs/integrations/litellm) |
| n8n | Workflow automation | [n8n setup](https://claudech.com/docs/integrations/n8n) |

Using a tool that is not listed? If it has an "OpenAI-compatible" or "custom base URL" setting, the three values above are all it needs. For plain SDK code, see [SDKs & libraries](https://claudech.com/docs/sdks).

## Troubleshooting

| Symptom | Cause | Fix |
| --- | --- | --- |
| `401 invalid_api_key` | Key pasted with whitespace, or a revoked key | Re-copy the key; check its status under **API keys** |
| `404 model_not_found` | Tool is sending a model name Claudech does not know and the unknown-model fallback is off | Use a Claudech slug from `GET /v1/models`; do not prefix it with a vendor name |
| Response `model` differs from the one you asked for | The tool asked for a vendor name (e.g. `gpt-4o`); Claudech served your default model instead of failing | Add the Claudech slug in the tool and select it; the `x-claud-model` header always names the model that ran |
| `403 model_not_in_plan` | Model is not included in your plan | Upgrade, or pick a model your plan allows |
| `402 insufficient_balance` | Wallet is empty | Top up under **Billing**; no KYC or card required |
| Tool says "verification failed" or "Invalid API key" on the first message | Base URL has a trailing slash, is missing `/v1`, or the key has whitespace | Use exactly `https://api.claudech.com/v1`; re-copy the key |
| Cursor: **Add Custom Model** does nothing | The name matches one of Cursor's built-in models | Use the Claudech slug exactly (`claude-opus-5-5`), not a vendor name |
| PowerShell shows `Iâ€™m` instead of `I'm` | Windows PowerShell 5.1 console encoding, not the API | Run `$OutputEncoding = [Console]::OutputEncoding = [System.Text.UTF8Encoding]::new()` once per session, or use [PowerShell 7](https://learn.microsoft.com/powershell/scripting/install/installing-powershell-on-windows) |
| Claude Code: `Invalid option`, `Too big` or another request validation error | Usually the base URL points at the OpenAI-format address (`/v1` or `/v1/chat/completions`) | Set `ANTHROPIC_BASE_URL` to exactly `https://api.claudech.com`. Claudech accepts current Claude Code requests, including system messages, adaptive thinking and large tool definitions; if the error continues, contact support with the `x-request-id` |
| Cursor: "Invalid API key. Unauthorized User API key" and nothing appears in your Claudech usage | Cursor's own servers refused the request before contacting Claudech. Happens on Cursor's Free/Hobby plan (custom keys need Cursor Pro or higher), when the custom model name collides with a Cursor built-in, or when the base URL was not saved | Check your Cursor plan; rename the model to a unique id such as `claude-opus-5-5`; re-enter the base URL, save, restart Cursor, start a new chat. Verify with the PowerShell/curl example in the [Quickstart](https://claudech.com/docs/quickstart) — if that works, Claudech is fine |
| Streaming stops early | Tool timeout shorter than the response | Raise the tool's timeout or lower `max_tokens` |

Still stuck? Open a ticket from the [Support](https://claudech.com/support) page or email [support@claudech.com](mailto:support@claudech.com) with the `x-request-id` header of a failing request and we will trace it.

---

Source: https://claudech.com/docs/integrations
