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

# Introduction

There are several ways to query models on Fireworks:

* The [Fireworks Python client library](/tools-sdks/python-sdk)
* The [web UI](https://fireworks.ai)
* [LangChain](https://python.langchain.com/docs/integrations/providers/fireworks)
* Directly invoking the [REST API](/api-reference/post-completions) using your favorite tools or language
* The [OpenAI Python client](https://github.com/openai/openai-python)

To see a list of available models, check out our [model library](https://fireworks.ai/models).

Models on Fireworks can be hosted ("deployed") via *serverless* or *dedicated* deployments. A [serverless deployment](/getting-started/concepts#deployments-and-deployment-types) is a shared public deployment of a model that is priced per-token and subject to [rate limits](/serverless/rate-limits). Not all models are available serverlessly. To confirm if a model is available serverlessly, you can find it in the [model library](https://fireworks.ai/models) and look for the `Serverless` tag.

For workloads that exceed serverless rate limits or require models that are not available serverlessly, we offer you the ability to spin up dedicated model deployments. [On-demand deployments](/guides/ondemand-deployments) get billed by the GPU-second and are subject to capacity constraints. Enterprise accounts can purchase [reserved capacity deployments](/deployments/reservations) to get guaranteed access to compute with a fixed commitment.

## Test models using the model playground

All serverless models can be tested using the [model playground](https://fireworks.ai/playground), where you can evaluate how the model behavior changes with different parameters.