## Execute AI model

`client.AI.Run(ctx, modelName, params) (*AIRunResponseUnion, error)`

**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/).

### Parameters

- `modelName string`

- `params AIRunParams`

  - `AccountID param.Field[string]`

    Path param

  - `Text param.Field[string]`

    Body param: The text that you want to classify

### Returns

- `type AIRunResponseUnion interface{…}`

  An array of classification results for the input text

  - `type AIRunResponseTextClassification []AIRunResponseTextClassificationItem`

    An array of classification results for the input text

    - `Label string`

      The classification label assigned to the text (e.g., 'POSITIVE' or 'NEGATIVE')

    - `Score float64`

      Confidence score indicating the likelihood that the text belongs to the specified label

  - `UnionString`

  - `type AIRunResponseAudio struct{…}`

    - `Audio string`

      The generated audio in MP3 format, base64-encoded

  - `UnionString`

  - `type AIRunResponseTextEmbeddings struct{…}`

    - `Data [][]float64`

      Embeddings of the requested text values

    - `Shape []float64`

  - `type AIRunResponseAutomaticSpeechRecognition struct{…}`

    - `Text string`

      The transcription

    - `Vtt string`

    - `WordCount float64`

    - `Words []AIRunResponseAutomaticSpeechRecognitionWord`

      - `End float64`

        The ending second when the word completes

      - `Start float64`

        The second this word begins in the recording

      - `Word string`

  - `type AIRunResponseImageClassification []AIRunResponseImageClassificationItem`

    - `Label string`

      The predicted category or class for the input image based on analysis

    - `Score float64`

      A confidence value, between 0 and 1, indicating how certain the model is about the predicted label

  - `type AIRunResponseObjectDetection []AIRunResponseObjectDetectionItem`

    An array of detected objects within the input image

    - `Box AIRunResponseObjectDetectionBox`

      Coordinates defining the bounding box around the detected object

      - `Xmax float64`

        The x-coordinate of the bottom-right corner of the bounding box

      - `Xmin float64`

        The x-coordinate of the top-left corner of the bounding box

      - `Ymax float64`

        The y-coordinate of the bottom-right corner of the bounding box

      - `Ymin float64`

        The y-coordinate of the top-left corner of the bounding box

    - `Label string`

      The class label or name of the detected object

    - `Score float64`

      Confidence score indicating the likelihood that the detection is correct

  - `type AIRunResponseObject struct{…}`

    - `Response string`

      The generated text response from the model

    - `ToolCalls []AIRunResponseObjectToolCall`

      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 AIRunResponseObjectUsage`

      Usage statistics for the inference request

      - `CompletionTokens float64`

        Total number of tokens in output

      - `PromptTokens float64`

        Total number of tokens in input

      - `TotalTokens float64`

        Total number of input and output tokens

  - `UnionString`

  - `type AIRunResponseTranslation struct{…}`

    - `TranslatedText string`

      The translated text in the target language

  - `type AIRunResponseSummarization struct{…}`

    - `Summary string`

      The summarized version of the input text

  - `type AIRunResponseImageToText struct{…}`

    - `Description string`

  - `type AIRunResponseImageTextToText struct{…}`

    - `Description string`

  - `type AIRunResponseMultimodalEmbeddings struct{…}`

    - `Data [][]float64`

    - `Shape []float64`

### Example

```go
package main

import (
  "context"
  "fmt"

  "github.com/cloudflare/cloudflare-go"
  "github.com/cloudflare/cloudflare-go/ai"
  "github.com/cloudflare/cloudflare-go/option"
)

func main() {
  client := cloudflare.NewClient(
    option.WithAPIToken("Sn3lZJTBX6kkg7OdcBUAxOO963GEIyGQqnFTOFYY"),
  )
  response, err := client.AI.Run(
    context.TODO(),
    "model_name",
    ai.AIRunParams{
      AccountID: cloudflare.F("023e105f4ecef8ad9ca31a8372d0c353"),
    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", response)
}
```

#### Response

```json
{
  "result": [
    {
      "label": "label",
      "score": 0
    }
  ]
}
```