--- title: Execute AI model --- [Skip to content](#%5Ftop) [API Reference](https://developers.cloudflare.com/api/typescript) [AI](https://developers.cloudflare.com/api/typescript/resources/ai) Copy Markdown Open in **Claude** Open in **ChatGPT** Open in **Cursor** --- **Copy Markdown** **View as Markdown** # Execute AI model client.ai.run(stringmodelName, AIRunParamsparams, RequestOptionsoptions?): [AIRunResponse](https://developers.cloudflare.com/api/typescript/resources/ai#%28resource%29%20ai%20%3E%20%28model%29%20ai%5Frun%5Fresponse%20%3E%20%28schema%29) POST/accounts/{account\_id}/ai/run/{model\_name} This endpoint provides users with the capability to run specific AI models on-demand. By submitting the required input data, users can receive real-time predictions or results generated by the chosen AI model. The endpoint supports various AI model types, ensuring flexibility and adaptability for diverse use cases. Model specific inputs available in [Cloudflare Docs](https://developers.cloudflare.com/workers-ai/models/). ##### Security API Token The preferred authorization scheme for interacting with the Cloudflare API. [Create a token](https://developers.cloudflare.com/fundamentals/api/get-started/create-token/). **Example:**`Authorization: Bearer Sn3lZJTBX6kkg7OdcBUAxOO963GEIyGQqnFTOFYY` API Email + API Key The previous authorization scheme for interacting with the Cloudflare API, used in conjunction with a Global API key. **Example:**`X-Auth-Email: user@example.com` The previous authorization scheme for interacting with the Cloudflare API. When possible, use API tokens instead of Global API keys. **Example:**`X-Auth-Key: 144c9defac04969c7bfad8efaa8ea194` ##### Accepted Permissions (at least one required) `Workers AI Write` `Workers AI Read` ##### ParametersExpand Collapse modelName: string AIRunParams \= TextClassification | TextToImage | TextToSpeech | 12 more AIRunParamsBase { account\_id, text } account\_id: string Path param text: string Body param: The text that you want to classify minLength1 TextClassification extends AIRunParamsBase { account\_id, text } TextToImage extends AIRunParamsBase { account\_id, text } TextToSpeech extends AIRunParamsBase { account\_id, text } TextEmbeddings extends AIRunParamsBase { account\_id, text } AutomaticSpeechRecognition extends AIRunParamsBase { account\_id, text } ImageClassification extends AIRunParamsBase { account\_id, text } ObjectDetection extends AIRunParamsBase { account\_id, text } Prompt extends AIRunParamsBase { account\_id, text } Messages extends AIRunParamsBase { account\_id, text } Translation extends AIRunParamsBase { account\_id, text } Summarization extends AIRunParamsBase { account\_id, text } ImageToText extends AIRunParamsBase { account\_id, text } Variant12 extends AIRunParamsBase { account\_id, text } Variant13 extends AIRunParamsBase { account\_id, text } MultimodalEmbeddings extends AIRunParamsBase { account\_id, text } ##### ReturnsExpand Collapse AIRunResponse \= Array | Uploadable | Audio { audio } | 12 more An array of classification results for the input text One of the following: Array label?: string The classification label assigned to the text (e.g., ‘POSITIVE’ or ‘NEGATIVE’) score?: number Confidence score indicating the likelihood that the text belongs to the specified label Uploadable Audio { audio } audio?: string The generated audio in MP3 format, base64-encoded Uploadable TextEmbeddings { data, shape } data?: Array\> Embeddings of the requested text values shape?: Array AutomaticSpeechRecognition { text, vtt, word\_count, words } text: string The transcription vtt?: string word\_count?: number words?: Array end?: number The ending second when the word completes start?: number The second this word begins in the recording word?: string Array label?: string The predicted category or class for the input image based on analysis score?: number A confidence value, between 0 and 1, indicating how certain the model is about the predicted label Array box?: Box { xmax, xmin, ymax, ymin } Coordinates defining the bounding box around the detected object xmax?: number The x-coordinate of the bottom-right corner of the bounding box xmin?: number The x-coordinate of the top-left corner of the bounding box ymax?: number The y-coordinate of the bottom-right corner of the bounding box ymin?: number The y-coordinate of the top-left corner of the bounding box label?: string The class label or name of the detected object score?: number Confidence score indicating the likelihood that the detection is correct UnionMember8 { response, tool\_calls, usage } response: string The generated text response from the model tool\_calls?: Array An array of tool calls requests made during the response generation arguments?: unknown The arguments passed to be passed to the tool call request name?: string The name of the tool to be called usage?: Usage { completion\_tokens, prompt\_tokens, total\_tokens } Usage statistics for the inference request completion\_tokens?: number Total number of tokens in output prompt\_tokens?: number Total number of tokens in input total\_tokens?: number Total number of input and output tokens Uploadable Translation { translated\_text } translated\_text?: string The translated text in the target language Summarization { summary } summary?: string The summarized version of the input text ImageToText { description } description?: string ImageTextToText { description } description?: string MultimodalEmbeddings { data, shape } data?: Array\> shape?: Array ### Execute AI model TypeScript HTTPHTTP TypeScriptTypeScript PythonPython GoGo TerraformTerraform ``` import Cloudflare from 'cloudflare'; const client = new Cloudflare({ apiToken: process.env['CLOUDFLARE_API_TOKEN'], // This is the default and can be omitted }); const response = await client.ai.run('model_name', { account_id: '023e105f4ecef8ad9ca31a8372d0c353', text: 'x', }); console.log(response); ``` 200 example ``` { "result": [ { "label": "label", "score": 0 } ] } ``` ##### Returns Examples 200 example ``` { "result": [ { "label": "label", "score": 0 } ] } ```