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

# RECIPES

> Create a reusable configuration and launch a run from it.

A recipe is the reusable config a training, evaluation, or synthesis run
launches from. The easiest way to create one is to generate a JSON
template, edit it, then pass that file to `recipes create`.

The example below uses `--type training`, but the same flow works for
`evaluate` and `synthesis`.

## CREATE AND USE A RECIPE

<Steps>
  <Step title="Generate a template">
    Write a template to `recipe.json`:

    ```bash theme={null}
    oumi-cli recipes generate-template \
      --type training \
      --output json > recipe.json
    ```
  </Step>

  <Step title="Edit the recipe">
    Replace the placeholders and remove fields you do not need. After
    trimming, a training recipe can look like:

    ```json theme={null}
    {
      "displayName": "support-ticket-classifier",
      "recipeConfig": {
        "type": "train",
        "trainingConfig": {
          "model": { "modelName": "Qwen/Qwen3.5-4B-Base" },
          "data": { "train": { "datasets": [{ "datasetId": 1 }] } }
        }
      }
    }
    ```
  </Step>

  <Step title="Create the recipe">
    ```bash theme={null}
    oumi-cli recipes create \
      --type training \
      --input-json-file recipe.json \
      --output json
    ```
  </Step>
</Steps>

Full commands: [recipes reference](/cli/commands/recipes).