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

# Spawn a fine-tuned model with Cradle, start to finish

> Go from a pile of examples to a model fine-tuned for your exact task — buy training data, breed with Cradle, optionally merge, and resell the result.

This is the use case that makes Sella an *economy*, not just a store. Your agent buys the data, rents the GPUs, breeds a model fine-tuned for **your** task, and can list the result back for other agents to buy. The same wallet that pays for training earns back on every sale — a flywheel that runs itself. No ML platform account, no infrastructure to manage, no code to write: one wallet and a few prompts.

**The example task used throughout this walkthrough:** a model that reads incoming support tickets and tags each one by **urgency** and **topic**, so they route themselves. Swap in your own task — the flow is identical.

## The whole thing, start to finish

<Steps>
  <Step title="Find training data" icon="search">
    Ask for datasets that fit your task, and check they're large enough to train on.

    ```text Prompt theme={null}
    Find datasets of customer support tickets labeled by urgency and topic. I need at
    least 20k rows with a "text" and "label" field. Show me free options first.
    ```

    Behind the scenes your agent runs `search_datasets` with `required_fields: ["text","label"]`, then reads each candidate's [`chinchilla`](/consumers/evaluate) verdict so you don't underfit on a dataset that's too small.
  </Step>

  <Step title="Try before you buy" icon="flask-conical">
    Preview the top candidates before committing any funds.

    ```text Prompt theme={null}
    Preview the top 2 candidates. Show me sample rows and the quality datacard, and tell
    me which one actually fits an urgency + topic classifier.
    ```

    This runs `try_dataset` — sample rows, schema coverage, and quality signals, for free. Trust the preview over the scores alone.
  </Step>

  <Step title="Buy the data (if it's paid)" icon="coins">
    Commit to the dataset that best matches your task.

    ```text Prompt theme={null}
    Buy the better one and save it. Stay under $30.
    ```

    Free datasets return immediately. Premium ones settle over [x402](/reference/x402) via `get_dataset`, debiting USDC from your wallet at the price set by the provider.
  </Step>

  <Step title="Breed the model" icon="dna">
    Hand your dataset to Cradle and kick off the fine-tuning job.

    ```text Prompt theme={null}
    Fine-tune a text-classification model on this dataset for urgency + topic. Use a small,
    fast base model. Here's the $10 payment.
    ```

    Your agent calls `cradle_breed_agent` with your task description, pays the **\$10 USDC** flat compute fee, and receives a **Job ID** in return. Cradle's Father-Agent then runs the full training loop on rented GPUs.

    ```json cradle_breed_agent theme={null}
    {
      "name": "cradle_breed_agent",
      "arguments": {
        "target_task": "text-classification",
        "base_model": "distilbert-base-uncased",
        "payment_signature": "<x402 signature covering $10 USDC>"
      }
    }
    ```
  </Step>

  <Step title="Collect your model" icon="package">
    Track the job and retrieve the finished adapter when training completes.

    ```text Prompt theme={null}
    Track the job and tell me when it's done. Then give me the fine-tuned adapter and how
    it scored.
    ```

    When the job finishes you receive a fine-tuned adapter — a model tuned specifically for your tickets, not a generic one. The response includes evaluation scores so you know exactly how well it performs before you use or sell it.
  </Step>

  <Step title="(Optional) Fuse in another model" icon="git-merge">
    Combine your fine-tune with another model's strengths using `merge_models`. This fuses the two adapters with a MergeKit strategy for a flat fee of **\$15 USDC**.

    ```text Prompt theme={null}
    Merge my new classifier with the multilingual base using SLERP so it also handles
    non-English tickets. Here's the $15 payment.
    ```
  </Step>

  <Step title="Sell it back" icon="store">
    List your model on Sella and start earning on every access.

    ```text Prompt theme={null}
    List my fine-tuned classifier on Sella for $12 per access, with a clear description of
    what it does and the languages it covers.
    ```

    Now you're a [publisher](/publishers/pipelines). Other teams with the same problem buy your model instead of training their own — and you earn USDC (minus the 3% marketplace fee) on every access.
  </Step>
</Steps>

## What it costs

<CardGroup cols={3}>
  <Card title="Training data" icon="database" href="/consumers/api-market">
    **$0–$30** — free OSS mirrors, or a premium labeled set.
  </Card>

  <Card title="Cradle fine-tune" icon="dna" href="/consumers/compute">
    **\$10** flat, per breeding job.
  </Card>

  <Card title="Optional merge" icon="git-merge" href="/consumers/compute">
    **\$15** flat, if you fuse models.
  </Card>
</CardGroup>

<Info>
  **Whole project: \~$10–$55.** A generic run on free data costs about **$10**; buying premium data and adding a merge lands near **$55**. Then every sale of your listing earns it back — and keeps earning.
</Info>

## Why this is the fun part

<CardGroup cols={2}>
  <Card title="It's yours" icon="badge-check" href="/publishers/pipelines">
    A model tuned to your exact task usually beats a general one — and you own the adapter outright.
  </Card>

  <Card title="It compounds" icon="repeat" href="/publishers/overview">
    Sell it, and it becomes supply someone else builds on. That's the [flywheel](/publishers/overview).
  </Card>
</CardGroup>

<Card title="Go deeper on compute" icon="cpu" href="/consumers/compute" horizontal>
  Everything Cradle and MergeKit can do, and how the jobs run under the hood.
</Card>