Execute AI Model

Receive real-time predictions or results generated by the chosen AI model.

External Documentation

To learn more, visit the Cloudflare documentation.

​

Parameters

Parameter	Description
AI Model Type	Choose the type of the model that you want to execute to fill the corresponding parameters. Ensure that the model type correctly corresponds to the specified model name.
Account ID	Your Cloudflare Account ID.
Frequency Penalty	Decreases the likelihood of the model repeating the same lines verbatim.
Guidance	Controls how closely the generated image should adhere to the prompt - higher values make the image more aligned with the prompt.
Height	The height of the generated image in pixels.
Image	An array of integers that represent the image data constrained to 8-bit unsigned integer values.
Image	Comma separated list of 8-bit unsigned integers that represent the image.
Image	Separated list of integers that represent the image data constrained to 8-bit unsigned integer values.
Image	Comma separated list of 8-bit unsigned integers that represent the image.
Image Base64	A base64-encoded string of the input image (for use with image to image tasks).
Input Text	The text that you want the model to summarize.
Language	The language of speech (e.g. en for English fr for French etc.).
Mask	A Comma separated list of integers that represents mask image in 8-bit unsigned integer value.
Max Length	The maximum length of the generated summary in tokens.
Max Tokens	The maximum number of tokens to generate in the response.
Model Name	The name of the model to execute. For more information about the models see cloudflare workers-ai models.
Negative Prompt	Text describing elements to avoid in the generated image.
Number of Steps	The number of diffusion steps, higher values can improve quality but take longer.
Presence Penalty	Increases the likelihood of the model introducing new topics.
Prompt	A text description of the image you want to generate.
Prompt	Text you wish to convert into speech.
Prompt	The input text prompt for the model to generate a response.
Source Language	The language to translate from, for example ‘en’ for English, ‘fr’ for French.
Target Language	The language to translate to, for example ‘en’ for English, ‘fr’ for French.
Text	The text to translate.
Text Classification	The text that you want to classify as positive or negative.
Text To Embed	A comma separated list of text’s to be converted into embeddings by the AI model.
Width	The width of the generated image in pixels.

​

Example Output

{
	"result": {
		"translated_text": "Test de traduction"
	},
	"success": true,
	"errors": [],
	"messages": []
}