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

# Flash

> Train, deploy, and chat with custom LoRA models on managed infrastructure, from one CLI.

Flash is Freesolo's managed post-training service. You write a short config, run
one command, and Flash fine-tunes a model on managed infrastructure, then serves the
result behind an OpenAI-compatible endpoint. There's nothing to host, and every
command that talks to the platform is authenticated with your Freesolo API key.

<Card title="Get started in minutes" icon="rocket" href="/quickstart" horizontal>
  Install the CLI and go from an empty directory to a deployed model in a few
  minutes.
</Card>

## What you can do

<AccordionGroup>
  <Accordion title="Fine-tune a model on your own task" icon="dumbbell">
    Write a TOML config, run one command, and Flash trains a LoRA adapter (a
    small set of add-on weights) on top of a [supported base model](/reference/models). You pick the
    model and the task; Flash handles the training infrastructure. See
    [Training](/guides/training).

    ```bash theme={null}
    flash train config.toml
    ```
  </Accordion>

  <Accordion title="Teach a format from examples with SFT" icon="copy">
    Supervised fine-tuning learns from the prompt/answer pairs in your [dataset](/guides/datasets).
    Use it when you already have examples of the output you want.

    ```toml theme={null}
    algorithm = "sft"
    ```
  </Accordion>

  <Accordion title="Reward the behavior you want with GRPO" icon="trophy">
    Reinforcement learning scores the model's own completions with your
    [environment's](/guides/environments) reward and updates toward higher
    reward (see [How Flash works](/how-flash-works)). Use it when you can score
    an output but can't hand-write the perfect one.

    ```toml theme={null}
    algorithm = "grpo"
    ```
  </Accordion>

  <Accordion title="Serve it behind an OpenAI-compatible API" icon="comments">
    `flash deploy` registers the adapter with managed serving, then
    `flash chat` or any OpenAI client can call it with your Freesolo key. See
    [Deploy & chat](/guides/deploy-and-chat).

    ```bash theme={null}
    flash deploy <run-id>
    ```
  </Accordion>

  <Accordion title="See the cost before you spend" icon="dollar-sign">
    `--cost` prints the pre-flight estimate without submitting. You pay for the
    quoted training run cost and for the tokens you serve. Cancelled runs are
    repriced to the training steps they actually reached.

    ```bash theme={null}
    flash train config.toml --cost
    ```
  </Accordion>
</AccordionGroup>

## Where Flash fits

| I want to...                                     | Start here                                                                                     |
| ------------------------------------------------ | ---------------------------------------------------------------------------------------------- |
| Fine-tune from examples I already have           | [Training: SFT](/guides/training#choose-sft-or-grpo)                                           |
| Improve outputs I can score but can't hand-write | [Training: GRPO](/guides/training#choose-sft-or-grpo) and [Environments](/guides/environments) |
| Define the task and reward my model learns on    | [Environments](/guides/environments)                                                           |
| Call my model from my existing OpenAI code       | [Deploy & chat](/guides/deploy-and-chat#use-it-from-your-own-code)                             |
| Understand how a run actually works              | [How Flash works](/how-flash-works)                                                            |

## Next steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Install the CLI, log in, and ship your first run in a few minutes.
  </Card>

  <Card title="How Flash works" icon="diagram-project" href="/how-flash-works">
    The loop behind a run: base models, environments, algorithms, serving.
  </Card>

  <Card title="Training" icon="dumbbell" href="/guides/training">
    Write a config, submit a run, and follow it to completion.
  </Card>

  <Card title="Deploy & chat" icon="comments" href="/guides/deploy-and-chat">
    Serve an adapter, then chat with it over an OpenAI-compatible API.
  </Card>
</CardGroup>