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 Goose CLI using its official guide. With the install script, add CONFIGURE=false before bash (curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | CONFIGURE=false bash): its built-in setup does not offer Pearl, and leaving it stops the script before the PATH step. The script puts goose in ~/.local/bin; add export PATH="$HOME/.local/bin:$PATH" to your shell profile and open a new terminal. These commands configure the CLI on macOS or Linux. On Windows, custom provider files live under %APPDATA%\Block\goose\config\custom_providers. Installation instructions.
Get your connection settings
Open Integrations, select a model, then choose Goose. The screen uses your organization’s region. The examples below use the public global endpoint; replace it with your regional endpoint and replaceYOUR_MODEL_ID with the full model ID shown there. Choose one of the models listed for this integration.
Set your Pearl API key in the terminal where you run Goose:
Configure Goose
Save the custom Pearl provider JSON in Goose’s custom_providers directory. For Messages, base_url is the endpoint origin without /v1, because Goose adds /v1/messages itself. For Chat Completions, it includes the complete chat/completions path. The key comes from PEARL_API_KEY. Pearl chat models support all three API formats. For this Goose setup, choose Messages or Chat Completions and use one matching provider configuration with a model that supports tool calling.~/.config/goose/custom_providers/pearl.json
Start Goose
Choose another API format
Use exactly one provider configuration. Pearl chat models support all three API formats. Choose a format supported by your tool, and replace the provider entry when switching formats. Tool calling, reasoning, and image support vary by model. OpenAI Chat Completions~/.config/goose/custom_providers/pearl.json
Start Goose
Start using Goose
Start a Goose session with the Pearl provider and selected model. The first session asks whether to share anonymous usage data; answer either way. Ask Goose to read a file and make a small edit, then continue the conversation to keep the tool-result history.Troubleshooting
Choose the engine matching the API URL. Anthropic uses Messages; OpenAI uses Chat Completions in this guide. Do not change the path to /responses. A 401 for a URL ending in /v1/messages/v1/messages means the Messages base_url still has a path; use the origin only. If the provider is not found, check the file location and restart Goose.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.429or Anthropic529: 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.