> ## Documentation Index
> Fetch the complete documentation index at: https://docs.poolside.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Use Poolside models in Pi
> Configure Pi to use Poolside models.
## Watch the setup video
## Prerequisites
* You have Pi installed. Run `pi --version` to confirm the installation. For other installation options, including `npm` and Windows, see the [Pi Quickstart](https://pi.dev/docs/latest/quickstart).
* You have one of the following:
* A Poolside Platform API key. To create one, go to [platform.poolside.ai](https://platform.poolside.ai/).
* The base URL for your self-managed model endpoint, and its API key if the endpoint requires one.
* An OpenRouter API key with access to Poolside models. To create one, go to [OpenRouter API keys](https://openrouter.ai/keys).
## Steps
Pi finds custom providers in `~/.pi/agent/models.json`.
1. Make your Poolside Platform API key available as an environment variable. Add it to your shell profile.
```bash theme={null}
export POOLSIDE_API_KEY=""
```
2. Create or open `~/.pi/agent/models.json` and add Poolside as a provider.
To find model IDs for your access method, see [List available models](/api/openai-api-examples#list-available-models).
```json title="~/.pi/agent/models.json" theme={null}
{
"providers": {
"poolside": {
"baseUrl": "https://inference.poolside.ai/v1",
"api": "openai-completions",
"apiKey": "$POOLSIDE_API_KEY",
"models": [
{
"id": "",
"name": "Poolside model",
"reasoning": ,
"contextWindow": ,
"maxTokens":
}
]
}
}
}
```
Replace ``, ``, and `` with the values for the model you selected. See [Supported models](/get-started/supported-models) and [Custom Models](https://pi.dev/docs/latest/models).
3. In your terminal, run `pi`.
```bash theme={null}
pi
```
4. Run `/model`.
```text theme={null}
/model
```
5. Select the Poolside model you added.
6. Send a codebase question to confirm Pi responds with the selected Poolside model.
If you run Poolside model inference on your own infrastructure, use the model's OpenAI-compatible endpoint at `https:///v1`. Use the API key configured for the endpoint, if it requires one.
Pi finds custom providers in `~/.pi/agent/models.json`.
1. Make the API key for your model endpoint available as an environment variable in your shell profile. If the endpoint does not validate API keys, use any non-empty value, such as `local-test`.
```bash theme={null}
export POOLSIDE_API_KEY=""
```
2. Create or open `~/.pi/agent/models.json` and add Poolside as a provider.
To find model IDs for your access method, see [List available models](/api/openai-api-examples#list-available-models).
```json title="~/.pi/agent/models.json" theme={null}
{
"providers": {
"poolside": {
"baseUrl": "https:///v1",
"api": "openai-completions",
"apiKey": "$POOLSIDE_API_KEY",
"models": [
{
"id": "",
"name": "Poolside model",
"reasoning": ,
"contextWindow": ,
"maxTokens":
}
]
}
}
}
```
Replace ``, ``, and `` with the values configured for your model. Reasoning support depends on the deployed model and serving configuration. See [Custom Models](https://pi.dev/docs/latest/models).
3. In your terminal, run `pi`.
```bash theme={null}
pi
```
4. Run `/model`.
```text theme={null}
/model
```
5. Select the Poolside model you added.
6. Send a codebase question to confirm Pi responds with the selected Poolside model.
1. In your terminal, run `pi`.
```bash theme={null}
pi
```
2. Run `/login`.
```text theme={null}
/login
```
3. Select **OpenRouter**.
4. Select **Sign in with OpenRouter**, then complete the OAuth authorization flow in your browser.
This creates a user-controlled API key billed through your OpenRouter account. To use an existing API key instead, select **Use an API key** and paste the key.
5. Run `/model`.
```text theme={null}
/model
```
6. Search for a Poolside model served through OpenRouter.
OpenRouter may offer free and paid Poolside models. To see current availability, see [Poolside models on OpenRouter](https://openrouter.ai/poolside).
7. Select the model you want to use.
Pi ships with a generated model snapshot, so recently released models may not appear in `/model` on older Pi versions. To add a model yourself, see [Custom Models](https://pi.dev/docs/latest/models) in the Pi documentation.
8. Send a codebase question to confirm Pi responds with the selected Poolside model.
## Related resources
* [Coding agents](/tools#coding-agents)
* [Poolside API](/api/overview)
* [Supported models](/get-started/supported-models)
* [OpenRouter API keys](https://openrouter.ai/keys)
* [Poolside models on OpenRouter](https://openrouter.ai/poolside)
* [Pi documentation](https://pi.dev)