--- title: "JetBrains AI Assistant with EU-hosted models · Setup" description: "Connect JetBrains AI Assistant to open-weight models processed in EU data centres through its OpenAI-compatible provider, and assign them to IDE features." canonical: "https://inference.eu/integrations/jetbrains-ai-assistant/" language: "en" --- IDEs and editors · JetBrains AI Assistant # Use JetBrains AI Assistant with open-source models hosted in the EU JetBrains AI Assistant can use your own models through an OpenAI-compatible endpoint, with or without a JetBrains AI subscription. Connect inference.eu, assign its models to the assistant's features, and chat, code generation and commit messages in IntelliJ IDEA, PyCharm and the other JetBrains IDEs run on open-weight models in Europe. [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 In your JetBrains IDE, open Settings, Tools, AI Assistant, Providers & API keys. 3. 3 Under Third-party AI providers, choose OpenAI-compatible, enter the inference.eu base URL and your key, and click Test Connection. 4. 4 In Models Assignment, choose an inference.eu model for Core features and one for Instant helpers, then click Apply. 5. 5 Open AI Chat, pick an inference.eu model in the model selector and send a test question about your project. Settings → Tools → AI Assistant → Providers & API keys ``` # Third-party AI providers Provider: OpenAI-compatible URL: https://api.inference.eu/v1 API key: # value of INFERENCE_EU_API_KEY # Click Test Connection, then Apply. # Models Assignment (needed for features outside AI Chat) Core features: qwen3-coder-480b-a35b-instruct Instant helpers: gpt-oss-120b ``` ## What JetBrains AI Assistant is JetBrains AI Assistant is the AI plugin for IntelliJ IDEA, PyCharm, WebStorm, GoLand and the other JetBrains IDEs. It provides AI Chat with project context, in-editor code generation, explanations, test and documentation generation, commit messages and integrated agents. By default it uses models provided through the JetBrains AI service. With bring your own key, it can also use third-party providers, including any endpoint compatible with the OpenAI API. That option is how you connect inference.eu and choose which models work on your code. ## How the configuration works In Providers & API keys, select OpenAI-compatible under Third-party AI providers, enter the inference.eu base URL ending in `/v1` and your key, and test the connection. The models then appear in a separate section of the AI Chat model selector and in the selector of compatible agents. Unlike OpenAI's own models, models from OpenAI-compatible endpoints are not assigned to features automatically. Until you assign them under Models Assignment, they are available only in AI Chat. Core features covers in-editor generation, commit messages and the default chat model; Instant helpers covers light tasks such as chat titles and name suggestions. Inline code completion is configured separately. ## Which models to choose For Core features, use a strong coding model such as `qwen3-coder-480b-a35b-instruct`; it handles code generation, refactoring suggestions and explanations well. `glm-5.3` and `kimi-k3` are good alternatives in AI Chat for longer discussions and design questions. For Instant helpers, pick a fast model such as `gpt-oss-120b`, since these calls happen often and should return quickly. AI completion features need a model built for fill-in-the-middle completion; general chat models are not suitable there. Keep JetBrains' default completion or turn it off if you have not chosen a dedicated completion model. ## Troubleshooting If Test Connection fails, check that the URL ends in `/v1` and that your network allows outbound HTTPS to the inference.eu host. A 401 response means the key is wrong. If models appear in AI Chat but features such as commit messages stay unavailable, you have not assigned models under Models Assignment yet. If the provider option is missing or locked, your organisation may manage AI centrally through JetBrains IDE Services or JetBrains Central; ask an administrator to allow third-party providers. When answers ignore tools or project context, try Qwen3 Coder or GLM-5.3, which handle tool calls more reliably. ## Keeping code and data in the EU When an inference.eu model handles a request, that request is processed in EU data centres and never used for training. We sign a data processing agreement under Article 28 GDPR, share our subprocessor list and bill in euros. Plan the rest of the setup carefully. If you also activate a JetBrains AI subscription, features your models do not cover fall back to JetBrains AI models. AI completion uses JetBrains models unless you configure another completion provider. For the strictest setups, use BYOK without JetBrains AI, assign inference.eu models to all features you need, and disable the features you have not assigned. ## JetBrains AI Assistant Category IDEs and editors Maker JetBrains API format OpenAI Processing EU data centres Website [www.jetbrains.com](https://www.jetbrains.com/ai-assistant/) Documentation [www.jetbrains.com](https://www.jetbrains.com/help/ai-assistant/use-custom-models.html) ## JetBrains AI Assistant: common questions The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly. Yes. Under Settings, Tools, AI Assistant, Providers & API keys, choose OpenAI-compatible as a third-party provider and enter a base URL and key. JetBrains documents this for any endpoint compatible with the OpenAI API, which includes inference.eu. No. Bring your own key works without a JetBrains AI subscription for AI Chat, the features your models support and compatible agents. Some features may be unavailable without the subscription, because JetBrains would otherwise serve them with its own models. Models from OpenAI-compatible endpoints are assigned to features manually. Open Models Assignment in Providers & API keys and pick inference.eu models for Core features and Instant helpers. Until then, they appear only in the AI Chat model selector. AI completion is configured separately and needs a model built for fill-in-the-middle completion. The chat models on this page are not designed for that. Use them for chat, generation and agents, and choose a dedicated completion model or keep completion off. Requests handled by your inference.eu models go to inference.eu. If a JetBrains AI subscription is also active, features your models do not support use JetBrains AI models instead. To avoid that, do not activate the subscription and disable unassigned features. Use Qwen3 Coder 480B for Core features, gpt-oss-120b for Instant helpers, and GLM-5.3 or Kimi K3 in AI Chat for longer discussions. Assign each one in Models Assignment so the IDE uses it outside chat as well. Your organisation may manage AI Assistant through JetBrains IDE Services or JetBrains Central, where an administrator decides which providers are allowed. Ask them to enable an OpenAI-compatible provider with the inference.eu URL for your profile. Yes, for agents that support API-key authentication. Models from your OpenAI-compatible provider appear in the model selector of compatible agents, so you can run agent tasks on inference.eu models and keep them on the same endpoint. Yes. The AI Assistant plugin and its provider settings are the same in IntelliJ IDEA, PyCharm, WebStorm, GoLand, PhpStorm, Rider and the other JetBrains IDEs that support AI Assistant. Configure it once per IDE installation. Usually the URL is wrong or the network blocks it. Use the inference.eu base URL ending in \`/v1\`, check for typos and trailing paths, and make sure a corporate proxy allows outbound HTTPS to the inference.eu host. [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/) - [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/) - [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/) ## 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