Skip to main content

Before you start

Complete organization setup, make sure your account has inference credit, and create a key on the API Keys page. Most coding agents need a tool-capable chat model; Aider’s basic edit workflow does not require native tool calling. Image input and reasoning support depend on the model. These terminal examples use Bash or Zsh on macOS, Linux, or Windows through WSL. Install the Cline extension in VS Code using its official installation guide. Open a project folder and click the Cline icon in the Activity Bar. On first launch, choose Bring my own API key and click Continue; if Cline is already set up, open its settings with the gear icon. Select OpenAI Compatible as the API Provider. This guide covers the VS Code extension.

Get your connection settings

Open Integrations, select a model, then choose Cline. The screen uses your organization’s region. The examples below use the public global endpoint; replace it with your regional endpoint and replace YOUR_MODEL_ID with the full model ID shown there. Choose one of the models listed for this integration. Paste your Pearl API key into Cline’s API key field. Enter the key itself, not an environment variable name.

Configure Cline

Cline provider fields
Model Configuration fields (expand the section below Model ID)
The OpenAI Compatible API Key field expects the actual key, not the literal text $PEARL_API_KEY. Enter the model ID verbatim. Supports Images, Context Window Size and Max Output Tokens are in the Model Configuration section, which starts collapsed. Left unchanged, Cline assumes a 128,000-token context window and image input, so set them from the selected model in the model catalog; turn Supports Images off for text-only models. If you enable Use different models for Plan and Act modes, apply the same settings to both. Click Continue (or save the settings), then start a new task.

Start using Cline

Open a project folder and start a new conversation. Ask Cline to explain a file or make a small change, then approve the file operations you want it to perform. You can review your usage and costs on the Analytics page.

Troubleshooting

  • 401: check the key and allow time for a newly created key to reach the inference gateway.
  • 404: copy the endpoint and exact model ID from Integrations. OpenAI base URLs end in /v1; the Anthropic SDK and Claude Code use the URL without that suffix.
  • 402: check your organization’s credit and billing status.
  • 429 or Anthropic 529: respect retry instructions and reduce concurrency.
  • For truncated output, check the output limit and reasoning budget. Increase limits only within the model’s maximum output length.