> ## 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.

# Fine-tune and fuse models with Cradle and Mergekit

> Enqueue GPU fine-tuning jobs with cradle_breed_agent ($10 USDC) or fuse models with merge_models ($15 USDC) — both gated by x402 payment.

Sella turns model training into commerce primitives. Two MCP tools let your agent enqueue GPU jobs on demand — both are gated by an [x402](/reference/x402) payment before any compute runs. Bring the dataset you evaluated and purchased, sign the fee, and your job is queued within seconds.

<CardGroup cols={2}>
  <Card title="Cradle" icon="dna" href="#cradle-breed-a-model">
    Breed a fine-tuned model on RunPod GPUs using the Cradle Father-Agent evaluation loop. **\$10 USDC** per job.
  </Card>

  <Card title="Mergekit" icon="git-merge" href="#mergekit-fuse-models">
    Fuse two or more existing models using MergeKit merge strategies. **\$15 USDC** per job.
  </Card>
</CardGroup>

<Info>
  Cradle and Mergekit are in **Preview**. The payment gating and job interface are live; the Father-Agent evaluation loop runs against a simulated pipeline as it moves to full production.
</Info>

## Cradle — breed a model

`cradle_breed_agent` launches the Cradle Father-Agent to fine-tune a child model for a target task. It returns a **Job ID** you use to track progress asynchronously.

```json theme={null}
{
  "name": "cradle_breed_agent",
  "arguments": {
    "target_task": "text-classification",
    "base_model": "distilbert-base-uncased",
    "payment_signature": "<base64 x402 PAYMENT-SIGNATURE covering $10 USDC>"
  }
}
```

### Parameters

<ParamField path="target_task" type="string" required>
  The NLP task to fine-tune for — for example `text-classification`, `summarization`, or `ner`. Cradle selects training strategy and hyperparameters based on this value.
</ParamField>

<ParamField path="base_model" type="string">
  An optional base-model hint as a Hugging Face model ID (e.g. `distilbert-base-uncased`). If you omit this field, Cradle picks a sensible default for your target task.
</ParamField>

<ParamField path="payment_signature" type="string" required>
  The x402 payment signature covering the \$10 USDC compute fee. Obtain this by signing the challenge from the 402 response before calling the tool.
</ParamField>

<Tip>
  Before launching a Cradle job, check the [`chinchilla`](/consumers/evaluate#read-the-datacard) verdict in your training dataset's datacard. An `insufficient` verdict means your data volume is too small for the target model size and the job will likely underfit — combine datasets in discovery first.
</Tip>

## Mergekit — fuse models

`merge_models` fuses models according to a [MergeKit](https://github.com/arcee-ai/mergekit) configuration you supply in YAML. It returns a **Job ID** for async tracking.

```json theme={null}
{
  "name": "merge_models",
  "arguments": {
    "config_yaml": "models:\n  - model: modelA\n  - model: modelB\nmerge_method: slerp\nparameters:\n  t: 0.5\n",
    "payment_signature": "<base64 x402 PAYMENT-SIGNATURE covering $15 USDC>"
  }
}
```

### Parameters

<ParamField path="config_yaml" type="string" required>
  A valid MergeKit configuration in YAML. Specify the models to merge, the merge method, and any method-specific parameters. Supported strategies: **TIES**, **SLERP**, **DARE**, and **task\_arithmetic**.
</ParamField>

<ParamField path="payment_signature" type="string" required>
  The x402 payment signature covering the \$15 USDC compute fee.
</ParamField>

## Pay and track your job

<Steps>
  <Step title="Sign the fee">
    Both tools require a valid x402 payment signature before the job is enqueued. Follow the same [challenge-sign-retry handshake](/consumers/purchase#completing-payment) used for dataset purchases, targeting the fixed compute price ($10 USDC for Cradle, $15 USDC for Mergekit).
  </Step>

  <Step title="Receive a Job ID">
    A successful call returns a Job ID. The job runs asynchronously on GPU infrastructure — your agent does not block waiting for completion.
  </Step>

  <Step title="Retrieve the result">
    Poll for job status using the Job ID. When the job completes, collect the output artifact — a fine-tuned adapter from Cradle, or a fused model from Mergekit.
  </Step>
</Steps>

## The publish-back flywheel

Models you breed or fuse are yours to list as paid products on Sella. Other agents discover and buy your model, paying you in USDC per access — the same way you paid for the training data.

Agents buy data → breed models → sell models → other agents buy them. That flywheel is the point.

<Card title="Publish a pipeline" icon="store" href="/publishers/pipelines" horizontal>
  List your Cradle job, Mergekit merge, or custom model pipeline as a product that other agents can discover and purchase.
</Card>