--- title: "Cursor with EU-hosted open models · Setup guide" description: "Use open-weight models processed in EU data centres for Cursor Chat and Agent through the OpenAI base URL override. What it covers and what still goes via Cursor." canonical: "https://inference.eu/integrations/cursor/" language: "en" --- IDEs and editors · Cursor # Use Cursor with open-source models hosted in the EU Cursor lets you add your own OpenAI-compatible endpoint for Chat and Agent. Point it at inference.eu and those requests are answered by open-weight models in European data centres. This page shows the setup and is clear about what still passes through Cursor's own servers. [Contact sales](https://inference.eu/contact/)[Setup](#setup) 1. 01API format: OpenAI 2. 02EU data centres 3. 03Covered by one DPA ## Set it up in a few minutes 1. 1 Create an API key in your inference.eu account. 2. 2 Open Cursor Settings, go to Models, paste the key into OpenAI API Key and turn on Use OpenAI API Key. 3. 3 Turn on Override OpenAI Base URL and enter the inference.eu base URL ending in `/v1`. 4. 4 Add each model you want as a custom model, using the exact inference.eu model id. 5. 5 Open a new Chat or Agent session, select the custom model and send a short prompt to confirm it answers. Cursor Settings → Models ``` # API Keys section OpenAI API Key: # value of INFERENCE_EU_API_KEY Use OpenAI API Key: on Override OpenAI Base URL: on Base URL: https://api.inference.eu/v1 # Models section → Add custom model (use the exact model id) Custom models: - qwen3-coder-480b-a35b-instruct - glm-5.3 - kimi-k3 ``` ## What Cursor is Cursor is an AI code editor built on VS Code, made by Anysphere. It combines Tab completion, a chat panel, inline edits and an Agent mode that plans changes across files and runs terminal commands. By default it uses models that Cursor provides under its own subscription. Cursor also accepts your own API keys, and for OpenAI-format providers it offers a base URL override. That is how you connect a custom OpenAI-compatible endpoint such as inference.eu and use open-weight models in Chat and Agent. ## How the configuration works In Settings, Models, the OpenAI API Key field takes your inference.eu key and Override OpenAI Base URL takes our base URL. Then add custom models by id. Cursor sends requests for those models in the OpenAI Chat Completions format to the overridden URL. Two details matter. First, the override is global: while it is on, OpenAI-family requests go to your endpoint, so turn it off when you want to use Cursor's own models. Second, on Business and Enterprise teams an admin must allow personal API keys under Team Settings, Models, or custom models are refused. Avoid model names that start with `claude-`, which Cursor treats as Anthropic models. ## Which models to choose Agent mode makes many tool calls in a row, so use models that are reliable with tools. `qwen3-coder-480b-a35b-instruct` is a strong default for edits, refactors and tests. `glm-5.3` and `kimi-k3` handle longer plans and explanations of unfamiliar code well. For quick questions in Chat, `gpt-oss-120b` responds fast. You can add several custom models and switch between them in the model picker. Cursor's Tab completion is not affected by any of this: it always runs on Cursor's own completion model and cannot be pointed at a custom endpoint. ## Troubleshooting "Invalid API key" or a 401 means the key is wrong or Cursor is still sending your inference.eu key to OpenAI because the override is off. "Model not found" or "This model does not support custom API keys" usually means the custom model name differs from the inference.eu id, or your team admin has not enabled personal OpenAI keys. If Cursor's own models stop working after setup, that is the global override at work; switch it off to use them. If the Settings fields do not take focus in some 3.15 builds, update Cursor. When Agent describes changes without applying them, the model is not returning tool calls; switch to one of the coding models above. ## Where your code goes Be clear about the path. Cursor routes every request through its own servers for final prompt building, including requests that use your key and custom base URL. Your code therefore passes through Cursor's backend before it reaches inference.eu. Cursor's zero data retention policy does not apply to requests made with your own keys. Tab completion and other features keep using Cursor's own models. What inference.eu covers is the model step: requests we receive are processed in EU data centres, never used for training, and covered by our Article 28 GDPR data processing agreement and subprocessor list, billed in euros. If no traffic may pass a US service, choose an editor that calls the endpoint directly. ## Cursor Category IDEs and editors Maker Anysphere API format OpenAI Processing EU data centres Website [cursor.com](https://cursor.com/) Documentation [cursor.com](https://cursor.com/docs/enterprise/privacy-and-data-governance) ## Cursor: common questions The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly. Cursor routes all requests through its own servers for prompt building, including those that use your key and custom base URL. Your code passes through Cursor's infrastructure before inference.eu processes it in the EU. For a direct path from your machine, use a client such as Continue, Cline or Zed. Yes, for Chat and Agent. Add your inference.eu key in the OpenAI API Key field, turn on Override OpenAI Base URL, enter our base URL and add custom models by id. Tab completion keeps using Cursor's own model. No. Custom API keys and the base URL override only apply to Chat and Agent. Tab completion and next-edit suggestions run on Cursor's own model and cannot be pointed at a custom OpenAI-compatible endpoint. The base URL override is global. While it is on, Cursor sends OpenAI-family requests to your endpoint, including some for its own models, which then fail. Turn the override off to use Cursor's models and back on for inference.eu models. Using your own key means inference.eu bills the model usage, in euros. Cursor itself still requires an account, and features such as Tab completion are part of Cursor's plans. Check Cursor's current plans for which tier fits your team. No. Cursor states that its zero data retention policy does not apply when you use your own API keys. Data handling at the model step then follows the provider's terms. At inference.eu, requests are processed in the EU and are never used for training. Usually your team admin has not allowed personal OpenAI keys under Team Settings, Models, Personal API Keys, or the custom model name does not match the inference.eu id exactly. Model names beginning with \`claude-\` are also treated as Anthropic models. Start with qwen3-coder-480b-a35b-instruct for code changes. GLM-5.3 and Kimi K3 are good for longer plans, and gpt-oss-120b is quick in Chat. All of them support the tool calls that Agent depends on. Not at the same time, because the base URL override applies to all OpenAI-family requests. Cursor has acknowledged requests for per-model base URLs. Until then, toggle the override when you switch between Cursor's models and your custom ones. Only partly. inference.eu processes the model requests in the EU, but they first pass through Cursor's servers, and Tab completion stays on Cursor's models. If your policy forbids any third-country transit, use a client that sends requests straight from your machine to inference.eu. [Ask a question](https://inference.eu/contact/) ## Related [All integrations](https://inference.eu/integrations/) - [ContinueConfigure the Continue extension for VS Code and JetBrains to use open-weight models processed in EU data centres, role by role, in config.yaml.IDEs and editors](https://inference.eu/integrations/continue/) - [ClineConnect the Cline coding agent for VS Code and the terminal to open-weight models processed in EU data centres with the OpenAI Compatible provider.Coding agents](https://inference.eu/integrations/cline/) - [Kilo CodeAdd inference.eu as a custom OpenAI-compatible provider in Kilo Code for VS Code and the CLI, and run its agents on open-weight models processed in the EU.Coding agents](https://inference.eu/integrations/kilo-code/) - [ZedAdd inference.eu as an OpenAI-compatible provider in the Zed editor and run its Agent Panel on open-weight models processed in EU data centres.IDEs and editors](https://inference.eu/integrations/zed/) ## Move your AI workloads to EU infrastructure Tell us which models you use and roughly how much traffic you have. We reply within one working day with pricing and next steps. - Reply within one working day - Pricing for your volume - DPA ready to sign