Use Poolside models in Goose - Poolside

Watch the setup video

Poolside with Goose

Prerequisites

Steps

Goose splits the endpoint into a host and a base path, rather than taking a single base URL.

  1. In your terminal, run goose configure.
   goose configure
  1. Select Configure Providers.
  2. Select OpenAI.
  3. When prompted for OPENAI_API_KEY, paste your Poolside API key.
  4. For OPENAI_HOST, enter https://inference.poolside.ai. Do not include /v1. The base path covers it.
  5. For OPENAI_BASE_PATH, keep the default, v1/chat/completions.
  6. Enter the model ID for an available Poolside model. To find model IDs for your access method, see List available models. Goose checks the configuration and saves it. To rename the provider or connect multiple OpenAI-compatible endpoints, create a custom provider instead. See Configure LLM Provider in the Goose documentation.
  7. Start an interactive session from your project directory. In Goose CLI, run:
   goose session
  1. Send a codebase question to confirm Goose responds with the selected Poolside model.

Use this option if you already route your models through OpenRouter or want to compare Poolside models alongside others.

  1. Create an API key in your OpenRouter account settings.
  2. In your terminal, run goose configure.
   goose configure
  1. Select Configure Providers.
  2. Select OpenRouter.
  3. When prompted, paste your OpenRouter API key.
  4. Enter the model ID for an available Poolside model. OpenRouter may offer free and paid Poolside models. To see current availability and model IDs, see Poolside models on OpenRouter.
  5. Start an interactive session from your project directory. In Goose CLI, run:
   goose session
  1. Send a codebase question to confirm Goose responds with the selected Poolside model.