---
title: "Cline with EU-hosted open models · Setup guide"
description: "Connect the Cline coding agent for VS Code and the terminal to open-weight models processed in EU data centres with the OpenAI Compatible provider."
canonical: "https://inference.eu/integrations/cline/"
language: "en"
---

Coding agents · Cline

# Use Cline with open-source models hosted in the EU

Cline is an open-source coding agent for VS Code, JetBrains and the terminal. Its OpenAI Compatible provider takes a base URL, a key and a model id, so connecting inference.eu takes a minute. Plans, file edits and command output are then processed by open-weight models in European data centres.

[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 the Cline panel, open settings with the gear icon and choose OpenAI Compatible as the API provider.

3.  3

    Enter the inference.eu base URL ending in `/v1`, your API key and a model id such as `qwen3-coder-480b-a35b-instruct`.

4.  4

    Under Model Configuration, set the context window and maximum output tokens for the model.

5.  5

    Start a task in Plan mode, review the plan, then switch to Act mode to confirm that edits and commands work.

6.  6

    For the terminal, run `cline auth -p openai -k "$INFERENCE_EU_API_KEY" -b <base URL> -m <model id>` once.

Cline CLI

```
# Cline CLI: configure the OpenAI Compatible provider in one command.
cline auth -p openai \
  -k "$INFERENCE_EU_API_KEY" \
  -b https://api.inference.eu/v1 \
  -m qwen3-coder-480b-a35b-instruct

# VS Code extension: Settings (gear icon) → API Provider: OpenAI Compatible
#   Base URL: https://api.inference.eu/v1
#   API Key:  your inference.eu key
#   Model ID: qwen3-coder-480b-a35b-instruct
```

## What Cline is

Cline is an open-source autonomous coding agent. It runs as an extension in VS Code and JetBrains IDEs and as a command-line tool. It reads files, writes and edits code, runs terminal commands and can use a browser, asking for approval at each step unless you allow actions automatically. Plan and Act modes separate thinking about a task from carrying it out.

Cline works with many model providers. Its OpenAI Compatible option accepts any endpoint that implements the OpenAI Chat Completions API, which is how you run it on open-weight models at inference.eu.

## How the configuration works

In the extension, choose OpenAI Compatible as the API provider and fill in three fields: Base URL, API Key and Model ID. The base URL is the inference.eu URL ending in `/v1`; Cline adds `/chat/completions` itself. The key is stored in your editor's secret storage.

The Model Configuration section lets you tell Cline the context window, maximum output tokens and whether the model accepts images. Cline uses these numbers to decide when to condense the conversation, so set them to the values listed for the model. In the CLI, `cline auth` with the `-p openai`, `-k`, `-b` and `-m` flags writes the same settings without the interactive wizard.

## Which models to choose

Cline sends long system prompts and relies on tool calls for every action, so model choice matters. `qwen3-coder-480b-a35b-instruct` is a strong default for Act mode: it is trained for agentic coding and follows tool formats closely. `glm-5.3` and `kimi-k3` are good Plan mode models when a task needs careful reasoning across many files.

Cline lets you set separate models for Plan and Act. A common pattern is GLM-5.3 or Kimi K3 to plan and Qwen3 Coder to act. `gpt-oss-120b` is fast and works well for small, well-defined tasks.

## Troubleshooting

"Invalid API Key" or a 401 means the key is wrong or was pasted with spaces. "Model Not Found" means the Model ID differs from the inference.eu id; copy it exactly. Connection errors usually come from a base URL with a typo or an extra path such as `/chat/completions`.

If Cline reports that the model did not use a tool, or loops on the same step, the model is struggling with tool calls; switch to Qwen3 Coder, GLM-5.3 or Kimi K3. If long tasks stop abruptly, check the context window you entered: a value larger than the model supports leads to rejected requests.

## Keeping code and data in the EU

Cline runs on your machine and sends model requests directly to the provider you configure. With inference.eu, your code, terminal output and task history are 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.

Cline can collect anonymous telemetry, which you can turn off in its settings. Do not sign in to the Cline provider if you want all model traffic to go to inference.eu; the OpenAI Compatible provider uses only the base URL and key you enter.

## Cline

Category

Coding agents

Maker

Cline Bot Inc.

API format

OpenAI

Processing

EU data centres

Website

[cline.bot](https://cline.bot/)

Documentation

[docs.cline.bot](https://docs.cline.bot/provider-config/openai-compatible)

## Cline: common questions

The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly.

Yes. Choose OpenAI Compatible as the API provider and enter the inference.eu base URL, key and model id. Cline then sends every model request to inference.eu. You need no account with Anthropic, OpenAI or Cline's own provider.

Qwen3 Coder 480B is a strong default for Act mode, and GLM-5.3 or Kimi K3 work well for Plan mode. All three handle the tool calls Cline relies on. Test them on a typical task from your backlog before deciding.

Not for model requests with the OpenAI Compatible provider. They go from your editor or terminal straight to inference.eu. Cline can collect anonymous telemetry, which you can switch off in its settings.

Run \`cline auth -p openai -k "$INFERENCE\_EU\_API\_KEY" -b <base URL> -m <model id>\`. The \`-b\` flag sets the OpenAI-compatible base URL. Run the command again with a different \`-m\` value to change models later.

Enter the context window listed for the model on inference.eu. Cline uses it to decide when to condense the conversation. A value that is too large causes rejected requests; one that is too small makes Cline condense earlier than needed.

Yes. Cline lets you set separate models for each mode. Many teams plan with GLM-5.3 or Kimi K3 and act with Qwen3 Coder, which keeps planning thorough and edits precise.

The model answered in plain text instead of returning a tool call. Use a model trained for tool use, such as Qwen3 Coder, GLM-5.3 or Kimi K3. Very long custom instructions can also push a model off format.

Yes. Cline is available for JetBrains IDEs as well as VS Code, and the OpenAI Compatible settings are the same: base URL, API key and model id. The CLI uses its own configuration set with \`cline auth\`.

Usually the base URL is wrong. It should be the inference.eu URL ending in \`/v1\`, without \`/chat/completions\`. Also check that your network or proxy allows outbound HTTPS to the inference.eu host.

Model requests are processed in EU data centres, never used for training, and covered by a data processing agreement under Article 28 GDPR with a published subprocessor list. Turn off Cline's telemetry and review the setup against your contract terms.

[Ask a question](https://inference.eu/contact/)

## Related

[All integrations](https://inference.eu/integrations/)

-   [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/)
-   [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/)
-   [Claude CodePoint Claude Code at inference.eu with ANTHROPIC\_BASE\_URL and run it on open-weight models processed in EU data centres. No Anthropic account needed.Coding agents](https://inference.eu/integrations/claude-code/)
-   [OpenCodeRun the OpenCode terminal agent on open-weight models processed in EU data centres. Add one provider block to opencode.json and keep your code in Europe.Coding agents](https://inference.eu/integrations/opencode/)

## 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