> ## Documentation Index
> Fetch the complete documentation index at: https://docs.suiri.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Choosing a Model

> Available models and how to interpret model specifications.

Suiri offers a selection of on-demand models optimized for different use cases.

***

## Available Models

To retrieve the current list of available models, query the models endpoint:

```bash theme={null}
export API_KEY="YOUR_API_KEY"

curl https://pulse.suiri.ai/v1/models \
  --header "Authorization: Bearer $API_KEY" | jq
```

This always reflects what is currently available on Suiri.

***

## How to Read Model Specifications

* **Context Window**: Maximum number of tokens (input + output) the model can process in a single request
* **Weights Precision**: Quantization level (Q4, Q8, FP8) — lower precision generally improves inference efficiency and reduces memory usage, but may affect output quality depending on the workload.