fofr/prompt-riff | API reference

Public

6 runs

Run fofr/prompt-riff with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
starting_prompt	string		The original prompt to create variations of
riff_context	string	Create creative variations that maintain the core concept but explore different angles, styles, moods, or perspectives	Instructions on how to riff or vary the original prompt
model	None	gpt-5-nano	Language model to use for generating variations
num_variations	integer	5 Min: 1 Max: 20	Number of prompt variations to generate

{
  "type": "object",
  "title": "Input",
  "required": [
    "starting_prompt"
  ],
  "properties": {
    "model": {
      "enum": [
        "claude-4-sonnet",
        "gpt-5",
        "gpt-5-mini",
        "gpt-5-nano"
      ],
      "type": "string",
      "title": "model",
      "description": "Language model to use for generating variations",
      "default": "gpt-5-nano",
      "x-order": 2
    },
    "riff_context": {
      "type": "string",
      "title": "Riff Context",
      "default": "Create creative variations that maintain the core concept but explore different angles, styles, moods, or perspectives",
      "x-order": 1,
      "description": "Instructions on how to riff or vary the original prompt"
    },
    "num_variations": {
      "type": "integer",
      "title": "Num Variations",
      "default": 5,
      "maximum": 20,
      "minimum": 1,
      "x-order": 3,
      "description": "Number of prompt variations to generate"
    },
    "starting_prompt": {
      "type": "string",
      "title": "Starting Prompt",
      "x-order": 0,
      "description": "The original prompt to create variations of"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "array",
  "items": {
    "type": "string"
  },
  "title": "Output"
}

Example API response

View prediction

['A real-life anime guy wearing a yellow zip-up hoodie unzipped and a green '
 "band tee with the word 'fofr' and a tropical monstera motif sits on a "
 'crowded London Underground carriage on his way home, listening to music from '
 'his phone on white wired earbuds as the city blurs past the windows.',
 'From a passenger’s perspective, a real-life anime guy in a bright yellow '
 "unzipped zip hoodie and a green band tee with 'fofr' and a repeating "
 'monstera pattern lounges on a busy London Underground train, his white wired '
 'earbuds plugged in and the beat letting him drift above the commute.',
 'Neon-noir mood: a real-life anime guy in a yellow zip-up hoodie left '
 "unzipped and a green 'fofr' monstera tee sits amid a sea of commuters on the "
 'London Underground, listening to music from his phone on white wired earbuds '
 'as the carriage hums.',
 'Evening rush on the Jubilee line: a real-life anime guy wearing a yellow '
 "zip-up hoodie unzipped and a green band shirt with 'fofr' and a tropical "
 'monstera motif sits on a packed train, headphones—white wired earbuds—tuned '
 'to the music from his phone while city lights flash outside.',
 'Editorial-ready moment: a real-life anime guy in a yellow unzipped zip '
 "hoodie and a green 'fofr' monstera tee sits on a bustling London Underground "
 "car, his white wired earbuds feeding his music as the carriage's reflections "
 'ripple over his face.']