--- title: OpenAI modules slug: openai-modules docTags: createdAt: 2025-03-12T12:47:49.143Z --- You can use the following OpenAI (ChatGPT, Whisper) modules to build your scenarios. The **Simple text prompt** module requires no setup, while other modules require connecting to the OpenAI (ChatGPT, Whisper) app. :::hint{type="warning"} If you encounter a `429` error, you've used all credits in your OpenAI account or exceeded your monthly OpenAI budget. To adjust your billing, see the [OpenAI billing settings](https://platform.openai.com/settings/organization/billing/overview). ::: # Get started ::::ExpandableHeading ## Simple text prompt :::hint{type="info"} On Free plans and trials, the** Simple text prompt** module supports only the **GPT-5 nano** model. To use other models, upgrade to a paid plan. ::: Generates a response based on a simple text prompt. The** Simple text prompt **module allows you to select a model and enter your prompt, with no other setup required. | **Field** | **Description** | | --------------- | ---------------------------------------------------- | | **Model** | Select the model that will generate the response. | | **Text prompt** | Enter text or instructions to generate the response. | The module uses credits based on the amount of input and output tokens consumed in each run. Input tokens depend on the prompt you enter, and output tokens are based on the response. After each run, you can see how many tokens were used in the module's output. This table shows how input and output tokens for OpenAI models convert to credits: | **Model name** | **Input tokens per credit** | **Output tokens per credit** | | --------------------------------------------- | --------------------------- | ---------------------------- | | GPT-6.1 Sol with over 272,000-token context | 226 | 60 | | GPT-6.1 Sol | 452 | 90 | | GPT-6 Sol with over 272,000-token context | 226 | 181 | | GPT-6 Sol | 452 | 90 | | GPT-6 Luna with over 272,000-token context | 4520 | 3616 | | GPT-6 Luna | 9040 | 1808 | | GPT 6 - Astra | 90 | 18 | | GPT-5.6 Sol with over 272,000-token context | 90 | 20 | | GPT-5.6 Sol | 181 | 30 | | GPT-5.6 Terra with over 272,000-token context | 226 | 50 | | GPT-5.6 Terra | 452 | 75 | | GPT-5.6 Luna with over 272,000-token context | 2260 | 502 | | GPT-5.6 Luna | 4520 | 753 | | GPT-5.5 | 181 | 30 | | GPT-5.4 | 181 | 40 | | GPT-5.4 nano | 4520 | 723 | | GPT-5.4 mini | 1205 | 201 | | GPT-5.4 with over 272,000-token context | 181 | 40 | | GPT-5.4 with up to 272,000-token context | 361 | 60 | | GPT-5.2 | 516 | 64 | | GPT-5.1 | 723 | 90 | | GPT-5 | 723 | 90 | | GPT-5 nano | 18080 | 2260 | | GPT-5 mini | 3616 | 452 | :::: # Responses and Conversations :::ExpandableHeading ## Generate a response Generates a response. | **Field** | **Description** | | --------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Model** | Select the model that will generate the response. | | **Prompt Type** | Use the default **Text prompt** or choose another prompt type for the response:
* Image prompt * File prompt * Reusable prompt * Advanced input | | **Reusable Prompt Definition ID** | You can create and manage your prompts [here](https://platform.openai.com/chat/edit). To copy the ID of the selected prompt, click the three-dots menu in the top-center and click the prompt ID. | | **Max Output Tokens** | Enter the upper limit for the number of tokens that can be generated for the response, including visible output tokens and reasoning tokens. | | **Tools** | Add one or more tools that the model may call while generating a response.
* **Type** - Select the type of tool to add: - Skills - File search - Function - Computer use preview - Web search preview - Web search preview (2025\_03\_11) - MCP - Code interpreter - Image generation - Custom | | **Tool Choice** | Select how the model should choose tools during response generation:
* None * Auto * Required * File search * Web search preview * Computer use preview * Code interpreter * Function * Custom * Allowed tools
If not selected, the default value is **Auto**. | | **Parallel Tool Calls** | Select whether the model can run tool calls in parallel. Defaults to **Yes**. | | **Run in Background** | Select if the query should run in the background, performed asynchronously.

This is recommended for long, research-heavy requests that may exceed time limits. | | **Context management** | Configure how the model's context is managed, for example, **compaction** to control token usage when conversations grow long.

**Context entry type**: Select how the context should be managed.

**Compact threshold**: Enter the token limit that triggers context compaction. When the number of tokens in the context exceeds this value, the module compacts the context to reduce token usage.
For more information, see [OpenAI compaction guide](https://developers.openai.com/api/docs/guides/compaction#server-side-compaction). | | **Conversation ID** | Provide a conversation ID for the model to generate a response within the context of that conversation, without you having to specify all previous messages (items). | | **Create a new conversation** | Select **Yes** if you don't provide a **Conversation ID **in the field above. A new conversation will be created automatically, and its ID will be output. | | **Temperature** | Enter the sampling temperature to use. Higher values like `0.8` will make the output more random, while lower values like `0.2` will make it more focused and deterministic. We generally recommend altering this or **Top P** but not both.
Must be lower than or equal to 2. | | **Top P** | Enter the nucleus sampling value, which is an alternative to sampling with temperature. This considers the results of the tokens with **Top P** probability mass. The value `0.1` means only the tokens comprising the top `10%` probability mass are considered. | | **Store** | Select whether to store the generated model response for later retrieval via API. Defaults to **Yes**. | | **Previous Response ID** | Enter the ID of the previous response to the module. | | **Instructions** | Enter a system (or developer) message as the first item in the model's context. When using along with **Previous Response ID**, the instructions from a previous response will not be carried over to the next response. | | **Reasoning** | **Effort **- Select how to model performs reasoning. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
**Summary** - Select the summary of the reasoning performed by the model. | | **Output Format** | **Type **- Select the format that the module must output
* Text * JSON schema * JSON object
The type of response format being defined. When **JSON object** is selected as the output format, the prompt must include the word `json`. | | **Truncation** | Select the truncation strategy to use for the model response.
* Auto * Disabled | | **Include** | Select additional output data to include in the model response. | | **Metadata** | Add key-value pairs that can be attached to an object. | ::: :::ExpandableHeading ## List input items Lists input items. | **Field** | **Description** | | --------------- | --------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Response ID** | Enter the ID of the response that you want to list the input items for. | | **Include** | Select the additional output data to include in the response. | | **Order** | Select the order to return the input items in. | | **Limit** | Enter the maximum number of returned results (bundles). | ::: :::ExpandableHeading ## Get a response Retrieves an existing model response. | **Field** | **Description** | | --------------- | ------------------------------------------------------------------------------ | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Response ID** | Enter the ID of the response that you want to retrieve the model response for. | ::: :::ExpandableHeading ## Delete a response Deletes an existing model response. | **Field** | **Description** | | --------------- | ---------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Response ID** | Enter the ID of the response that you want to delete the model response for. | ::: # Chat and Assistant :::ExpandableHeading ## Generate a completion Generates a chat completion. See the [OpenAI model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility) section for the list of supported models. | **Field** | **Description** | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Select Method** | Select a method to create a completion. | | **Model** | Select or map the model you want to use.
**Note**: Ensure you have access to the model you want to work with. Only models available for the account are listed for selection. | | **Messages** | Add the messages for which you want to create the completion by selecting the **Role** and entering the **Message Content**.
For some models, you can manage image input type and image details as well as audio filename and audio data.
For more information about chat completion, refer to the [OpenAI documentation](https://platform.openai.com/docs/guides/chat). | | **Response Format** | Choose the format for the response. When using JSON Object, you must also instruct the model to produce JSON via a System or User message. If not, the model can generate an unending stream of whitespace until it reaches the token limit. This will result in a long-running and seemingly "stuck" request. | | **Reasoning Effort** | Constrain the effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning) by selecting **low**, **medium**, or **high**. Reducing the reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Defaults to `medium`. | | **Max Output Tokens** | The maximum number of tokens to generate in the completion. The default value is 2048.
**Note**: Low values may cause the output to be truncated. High values may use a lot of OpenAI credit.
The o1 and o3 models require tokens for both output and reason. Insert the sum of both tokens if you use the o1 and o3 models.
Refer to [OpenAI Platform documentation](https://platform.openai.com/docs/guides/reasoning) to learn more about reasoning modules. | | **Temperature** | Specify the sampling temperature to use.
A higher value means the model will take more risks. Try 0.9 for more creative applications and 0 (argmax sampling) for ones with a well-defined answer. Defaults to 1. | | **Top P** | An alternative to sampling with temperature is called nucleus sampling, where the model considers the results of the tokens with top\_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. Defaults to 1. | | **Number** | The number of completions to generate for each prompt. Defaults to 1. | | **Frequency Penalty** | Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. This value must be a number between -2 and 2. | | **Presence Penalty** | Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. This value must be a number between -2 and 2. | | **Token Probability** | Add the token probability by selecting the **Token** and **Probability**. The **Probability** must be a number between -100 and 100. | | **Seed** | This feature is in Beta. If specified, OpenAI will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Refer to the `system_fingerprint` response parameter to monitor changes in the backend.
For more information, refer to the [OpenAI documentation](https://platform.openai.com/docs/guides/chat). | | **Tool Choice** | Select your tool choice:
* None (no tools) * Auto (AI decides to use tools or not) * Required (forces the AI to use the listed tool(s)) | | **Tools (functions)** | If you select Auto or Required for **Tool Choice**, click **+ Add tool** and enter the following:
* Type (required): Function or Custom * Name (required): Name of tool * Description: Description of the tool * Parameters Input Mode: Map or select Simple or Manual * Strict: Select Yes, No, or Empty | | **Stop Sequences** | Add up to 4 sequences where the API will stop generating further tokens. | | **Other Input Parameters** | Add any additional input parameters by selecting the **Parameter Name**, the **Input Type**, and entering the **Parameter Value**.
For more information, refer to the [OpenAI documentation](https://platform.openai.com/docs/guides/text-generation). | ::: :::ExpandableHeading ## Generate a moderation Qualifies whether the provided image or text(s) contain violent, hateful, illicit, or adult content. | **Field** | **Description** | | ---------------- | --------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Input format** | Select the format of the input content:
* Text * Array of texts * Image | | **Input text** | Enter the text for which you want to create the moderation. The module will classify the content against OpenAI's Content Policy. | | **Model** | Select or map the model you want to use. If empty, the default model will change based on the selected input format. | ::: # Files :::ExpandableHeading ## Add files to a vector store Adds files to a specified vector store or, if not specified, creates a new vector store based on the configuration. | **Field** | **Description** | | ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Batch Create Mode** | Choose if you would like to create a new vector store or choose an existing vector store. | | **Vector Store ID** | Select the vector store. | | **Vector Store Name** | Enter a name for a new vector store. | | **Days Expires After** | Enter the number of days of inactivity for the vector store. When the specified amount of days have passed, the vector store expires. | | **File IDs** | Select the files to add to a vector store. For a list of supported file formats, see [Open AI File Search supported files](https://platform.openai.com/docs/assistants/tools/file-search/supported-files). | ::: :::ExpandableHeading ## Upload a file Uploads a file that will be available for further usage across the OpenAI platform. | **Field** | **Description** | | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **File Name** | Enter the name of the file to be uploaded, including the file extension. For example, `myFile.png`.
Supported file types depend on the option selected in the **Purpose **field below. The **Fine Tune** purpose supports only `.jsonl` files. Assistants supports file types found in the OpenAI [Assistants Tools guide](https://platform.openai.com/docs/assistants/tools). Vision supports `.jpeg`, `.jpg`, `.png`, `.gif`, `.webp` files. Batch supports only `.jsonl`. | | **File Data** | Enter the file data to be uploaded. You can retrieve file data using the **HTTP: Get a file** module. | | **Purpose** | For [Assistants](https://developers.openai.com/api/docs/assistants/migration) and Messages select `Assistant`. For [Fine-tuning](https://developers.openai.com/api/reference/resources/fine_tuning), select `Fine Tune`. For Assistants image file inputs, select `Vision`. For uploading batches, select `Batch`. | ::: :::ExpandableHeading ## Download a container file Downloads a file from a container. | **Field** | **Description** | | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Container ID** | Enter (map) the ID of the container.

For example, you can find this ID in the output of the **Create a model response** module, when using a code interpreter tool that produces a image file as output.

**Example Container ID: **`cntr_687539c204348198b213bd1fa33c82090ebad0602fa` | | **File ID** | Enter (map) the ID of the file.

For example, you can find this IDs in the output of the **Create a model response** module, when using a code interpreter tool that produces a image file as output.

**Example File ID:**
`cfile_687539c9229081919afea08bc8ad1480` | ::: # Vector Stores :::ExpandableHeading ## Create a vector store or add files Creates a new vector store and optionally adds files to it, or adds files to an existing vector store. | **Field** | **Description** | | ---------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Batch create mode** | Choose whether to create a batch on an existing vector store or on a new one. | | **Vector store ID** | Select or map the vector store to add files to. Appears when you select **Choose vector store** in **Batch create mode**. | | **Vector store name** | Enter a name for the new vector store. Appears when you select **Create vector store** in **Batch create mode**. | | **Days expires after** | Enter the number of days of inactivity after which the vector store expires. Appears when you select **Create vector store** in **Batch create mode**. | | **File IDs** | Select the files to add to the vector store. For supported file formats, see [OpenAI File Search supported files](https://developers.openai.com/api/docs/guides/tools-file-search#supported-files). | | **Chunking strategy** | Select how the added files are split into chunks. Applies only when you add files. Defaults to **Auto**, which uses a chunk size of 800 tokens with a 400-token overlap. | ::: :::ExpandableHeading ## List vector stores Returns a list of vector stores. | **Field** | **Description** | | -------------- | ---------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Sort order** | Select the order to return the vector stores in, sorted by their creation time. | | **Limit** | Enter the maximum number of results to return and work with in one execution cycle. Ranges between 1 and 100, and defaults to 20. | ::: :::ExpandableHeading ## Search a vector store Searches a vector store and returns the file content chunks that match your query. | **Field** | **Description** | | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Vector store ID** | Select or map the vector store you want to search. | | **Queries** | Enter a natural-language search phrase, for example, `What is our refund policy for annual plans?` Add more queries to run several searches at once. Each query returns its own set of matching chunks in the output. | | **Filter** | Restrict the search to files whose custom attributes match the criteria you enter. Attributes are key/value metadata attached to files in the vector store on OpenAI's side. | | **Rewrite query** | Select **Yes** to let OpenAI rephrase your query for better semantic-search results. Useful for full-sentence or conversational queries. The rewritten text appears in the module's **Search query** output. | | **Ranking options** | **Ranker** enables re-ranking. Choose **Auto** to use the latest ranker, a specific ranker version (for example, `default-2024-11-15`), or **None** to disable re-ranking. | | **Limit** | Enter the maximum number of results to return and work with in one execution cycle. Ranges between 1 and 50. | ::: :::ExpandableHeading ## Delete a vector store Deletes a vector store. | **Field** | **Description** | | ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection in your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Vector store ID** | Select the vector store you want to delete, or map its ID. Deleting a vector store also removes it from any assistant or response that uses it. | ::: # Embeddings :::ExpandableHeading ## Generate an embedding Creates an embedding vector representing the input text. | **Field** | **Description** | | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection in your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Model** | Select or map the model you want to use to generate the embedding. | | **Input type** | Select whether to turn a single text or multiple texts into embeddings in one request. | | **Text** | Enter the text to turn into an embedding. Can't be empty or exceed 8192 tokens. | | **Dimensions** | Enter the number of dimensions for the resulting embedding. Must be higher than or equal to 1. Supported only in `text-embedding-3` and later models. Lower values reduce cost and meet vector database limits. If left empty, the model default is used: 1536 for `text-embedding-3-small` and 3072 for `text-embedding-3-large`. | | **Encoding format** | Select the format of the returned embeddings. **Float** is an array of numbers, and **Base64 **is a base64-encoded string. | | **User ID** | Enter a unique identifier for your end user to help OpenAI monitor and detect abuse. For details, see [OpenAI Safety best practices](https://platform.openai.com/docs/guides/safety-best-practices). | ::: # Images :::ExpandableHeading ## Generate images Generates images using GPT Image. | **Field** | **Description** | | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Model** | Select or map the model you want to use:
* GPT-Image-2.5 Flare * GPT-Image-2.5 Sunburst * GPT Image 2 * GPT Image 1.5 * GPT Image 1 * GPT Image 1 Mini
**Note**: Ensure you have access to the model you want to work with. Only models available for the account are listed for selection. | | **Prompt** | Enter details of the images you want to generate. | | **Size** | Select or map the size of the images to generate. It must be one of the available options:
* `1024x1024` (all models) * `1536x1024` (landscape) (all GPT Image models) * `1024x1536` (portrait) (all GPT Image models)
**Note:** If you select GPT-Image-2.5 Flare
GPT-Image-2.5 Sunburst, **Size **is a text field. | | **Quality ** | Select the image quality:
* Auto * Max * Extremely High * High * Medium * Low
If not selected, defaults to **Auto**. | | **Quality** | Select the quality of the generated image. HD generates images with finer details and greater consistency across the image. | | **Background** | Select the background:
* Auto * Transparent * Opaque
If not selected, defaults to **Auto**.
When using the **Transparent** option, the **Output Format**
must allow transparency (webp or png). | | **Output Format** | Select the output format:
* PNG * JPEG * WEBP
If not selected, defaults to **PNG**. | | **Number** | Enter the number of images to generate. Enter a number between 1 and 10. | | **Moderation** | Select the content-moderation level:
* Auto * Low
If not selected, defaults to **Auto**. A **Low** option provides a weaker (less restrictive) content filter. | | **Style** | Select the style:
* Vivid * Natural | | **Response Format** | Select or map the format in which the generated images are returned.
If you select `Base64-encoded`, the raw PNG image can be obtained by using the IML function, `toBinary(.data[].b64_json; base64)` in the subsequent modules. | ::: :::ExpandableHeading ## Analyze images (Vision) Accepts an array of images as an input and provides an analysis result for each of the images following the instructions specified in the prompt. | **Field** | **Description** | | ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Prompt** | Enter instructions for how to analyze the image(s). | | **Images** | Add or map the images you want to analyze.
You can add images by entering an **Image URL** or **Image file** data.
**Image URL**: Enter the URL address to a public resource of the image. For example, https\://getmyimage.com/myimage.png.
**Image file**: Map or select the binary data of the image. You can retrieve the binary data of an image using the **HTTP: Get a file** module, or another app such as **Dropbox**. | | **Model** | Select or map the model you want to use.
**Note**: Ensure you have access to the model you want to work with. Only models available for the account are listed for selection. | | **Max Completion Tokens** | Enter the maximum number of tokens to use for the completion. The default value is 2048. | | **Temperature** | Specify the sampling temperature to use.
Higher temperatures generate more diverse and creative responses. For example, `0.8`. Lower temperatures generate more focused and well-defined responses. For example, `0.2`. The default value is `1`.
The value must be lower than or equal to 2. | | **Top P** | Specify the Top P value to use nucleus sampling. This will consider the results of the tokens with probability mass. The default value is `1`.
The value must be lower than or equal to 1. | | **Number** | Enter the number of responses to generate. If more than 1 response is generated, the results can be found in the module's output within **Choices**. The default value is `1`. | ::: :::ExpandableHeading ## Edit images Creates an edited or extended image given one or more source images and a prompt. | **Field** | **Description** | | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Model** | Select or map the model you want to use:
* GPT-Image-2.5 Flare * GPT-Image-2.5 Sunburst * GPT Image 2 * GPT Image 1.5 * GPT Image 1 * GPT Image 1 Mini
**Note**: Ensure you have access to the model you want to work with. Only models available for the account are listed for selection. | | **Images** | Enter an image to edit.
**GPT Image **models: Each image must be in PNG, WEBP
or JPEG/JPG format, less than 25 MB. | | **Prompt** | Enter details of the images you want to edit. The maximum number of characters allowed for **GPT Image** models is 32000. | | **Quality**

| Select the image quality:
* Auto * Max * Extremely High * High * Medium * Low
If not selected, defaults to **Auto**. | | **Size** | Select or map the size of the images to generate. It must be one of the three options:
* `1024x1024` (all models) * `1536x1024` (landscape) (all GPT Image models) * `1024x1536` (portrait) (all GPT Image models)
**Note:** If you select GPT-Image-2.5 Flare
GPT-Image-2.5 Sunburst, **Size **is a text field. | | **Background** | Select the background:
* Auto * Transparent * Opaque
If not selected, defaults to **Auto**.
When using the **Transparent** option, the **Output Format**
must allow transparency (webp or png). | | **Output Format**
| Select the output format:
* PNG * JPEG * WEBP
If not selected, defaults to **PNG**. | | **Input Fidelity**
| Select how much effort the model will exert to match the style and features, especially facial features, of input images:
* Low * High
If not selected, defaults to **Low**. | | **Mask** | Enter an additional image with fully transparent areas (where alpha is zero). The transparent areas indicate where the Image will be edited. The file must be in PNG format, less than 4 MB, and the same dimensions as the Image you've entered. | | **Number** | Enter the number of images to generate. Enter a number between 1 and 10. | | **Response Format** | Select or map the format in which the generated images are returned.
If you select `Base64-encoded` PNG, the raw PNG image can be obtained by using the IML function, `toBinary(.data[].b64_json; base64)` in the subsequent modules. | ::: # Audio :::ExpandableHeading ## Generate speech from text Generates an audio file based on the text input and settings. | **Field** | **Description** | | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Input** | Enter text to generate into audio.
The text must be between 1 and 4096 characters long. | | **Model** | Select or map the model you want to use. Refer to the [OpenAI Audio API documentation](https://platform.openai.com/docs/api-reference/audio) for information on available models.
**Note**: Ensure you have access to the model you want to work with. Only models available for the account are listed for selection. | | **Voice** | Select or map the voice to use in the audio. For voice samples, see the [OpenAI Voice Options guide](https://platform.openai.com/docs/guides/text-to-speech/voice-options). | | **Output Filename** | Enter a name for the generated audio file. Do not include the file extension. | | **Response Format** | Select or map the file format for the generated audio file. | | **Speed** | Enter a value for the speed of the audio.
This must be a number between 0.25 and 4. | ::: :::ExpandableHeading ## Generate a transcription Transcribes an audio to text. | **Field** | **Description** | | ------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **File Name** | Enter the name of the file you want to transcribe. | | **File Data** | Enter the data of the file you want to transcribe. | | **Model** | Select or map the model you want to use. Refer to the [OpenAI Audio API documentation](https://platform.openai.com/docs/api-reference/audio) for information on available models.
**Note**: Ensure you have access to the model you want to work with. Only models available for the account are listed for selection. | | **Chunking Strategy** | This field appears if you select the following model in the **Generate a transcription** module:
`gpt-4o-transcribe-diarize`

Select how the module splits longer audio files into smaller parts before transcription. Choose **Auto** to apply recommended settings, or **Custom** to define your own chunking parameters.

This parameter must be provided if the input audio is longer than **30 seconds**. | | **Chunking Strategy Settings** | These fields appear when you select **Custom** in the **Chunking Strategy** field. Use them to control how the module detects speech and divides the audio before transcription.

**Prefix Padding**: Enter the amount of audio to include before speech detection (in milliseconds). Maximum value is 10000.

**Silence Duration**: Enter how long silence must last before the module detects that speech has stopped (in milliseconds). Maximum value is 10000.

**Thresold**: Enter the sensitivity level for voice activity detection. Higher values require louder audio for the model to detect speech. Maximum value is 1. | | **Prompt** | Enter text to guide the model's style or continue a previous audio segment. (Optional) The prompt should be in the same language as the audio. | | **Temperature** | Enter a sampling temperature between 0 and 1. Higher values, such as 0.8, will make the output more random. Lower values, such as 0.2, will make it more focused and deterministic. | | **Language** | Enter the two letter ISO code of the input audio's language. | ::: :::ExpandableHeading ## Generate a translation (Whisper) Translates an audio into English. | **Field** | **Description** | | --------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **File Name** | Enter the name of the file you want to translate. | | **File Data** | Enter the data of the file you want to translate. | | **Model** | Select or map the model you want to use. Refer to the [OpenAI Audio API documentation](https://platform.openai.com/docs/api-reference/audio) for information on available models.
**Note**: Ensure you have access to the model you want to work with. Only models available for the account are listed for selection. | | **Prompt** | Enter text to guide the model's style or continue a previous audio segment. (Optional) The prompt should be in English. | | **Temperature** | Enter a sampling temperature between 0 and 1. Higher values, such as 0.8, will make the output more random. Lower values, such as 0.2, will make it more focused and deterministic. | ::: # Skills :::hint{type="info"} When creating a new skill or version, it may not be immediately available. If you use the new ID in a subsequent module, consider adding a **Tools > Sleep** module to allow time for provisioning. ::: :::ExpandableHeading ## List skills Returns a list of skills. | **Field** | **Description** | | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Order** | Select how to sort the results by timestamp.
* **Ascending** returns the oldest items first * **Descending** returns the newest items first | | **Limit** | Enter the maximum number of results to return during one execution cycle. | ::: :::ExpandableHeading ## Get a Skill Returns information about a specific skill by its ID. | **Field** | **Description** | | -------------- | --------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Skill ID** | Enter the ID of the skill you want to retrieve. | ::: :::ExpandableHeading ## Download a skill Downloads a skill as a ZIP file using its ID. | **Field** | **Description** | | -------------- | --------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Skill ID** | Enter the ID of the skill you want to download. | ::: :::ExpandableHeading ## Create a skill Creates a new skill. | **Field** | **Description** | | -------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **File** | Select a file that contains the skill data from a previous module or switch to Map to provide your file. This file is used to create the skill. | | **File name** | Enter the name of the file that defines the skill. For example, `skill.zip`. | | **File data** | Enter the file data that contains the skill definition. The file must include a `SKILL.md` file at the root.

For details about Skill structure, see [OpenAI Skills overview](https://developers.openai.com/api/docs/guides/tools-skills). | ::: :::ExpandableHeading ## Update the default version pointer for a skill Updates the default version pointer for a skill. | **Field** | **Description** | | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Skill ID** | Enter the ID of the skill whose default version you want to update. | | **Default version** | Enter the version ID you want to set as the default. This version will be used when the skill is called without specifying a version. | ::: :::ExpandableHeading ## Delete a skill Deletes a skill. This action cannot be undone. | **Field** | **Description** | | -------------- | ------------------------------------------------------------------------------------------------------------------ | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Skill ID** | Enter the ID of the skill you want to delete. This removes the skill so it can no longer be used in your scenario. | ::: # Skills Versions :::ExpandableHeading ## List skill versions Returns a list of skill versions. | **Field** | **Description** | | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Skill ID** | Enter the ID of the skill whose versions you want to retrieve. | | **Order** | Select how to sort the results by timestamp.
* **Ascending** returns the oldest versions first * **Descending** returns the newest versions first | | **Limit** | Enter the maximum number of versions to return during one execution cycle. | ::: :::ExpandableHeading ## Get a skill version Returns information about a specific skill version. | **Field** | **Description** | | -------------- | -------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Skill ID** | Enter the ID of the skill whose version you want to retrieve. | | **Version** | Enter the version ID you want to retrieve. This returns the configuration of that specific version so you can use it in your scenario. | ::: :::ExpandableHeading ## Download a skill version Downloads a skill version as a ZIP file. | **Field** | **Description** | | -------------- | ------------------------------------------------------------------------------------------ | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Skill ID** | Enter the ID of the skill whose version you want to download. | | **Version** | Enter the version ID you want to download.This returns the file for that specific version. | ::: :::ExpandableHeading ## Create a skill version Creates a new immutable skill version. | **Field** | **Description** | | -------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Skill ID** | Enter the ID of the skill you want to add a new version to. | | **File** | Select the file that contains the skill version data. You can use the output of the previous module, or switch to **Map**. | | **Set as default version** | Select whether to set the new version as the skill’s default version. If you select **Yes**, OpenAI uses this version when the skill is called without a specific version. | ::: :::ExpandableHeading ## Delete a skill version Deletes a skill version. This action cannot be undone. | **Field** | **Description** | | -------------- | ---------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Skill ID** | Enter the ID of the skill that contains the version you want to delete. | | **Version** | Enter the version ID you want to delete. This removes the version so it can no longer be used. | ::: # Batches :::hint{type="info"} If you're using restricted permissions for your API key, enable the `files:read` permission in the [OpenAI API Platform](https://platform.openai.com/api-keys). This is a required permission for **Batch** modules. ::: :::ExpandableHeading ## Watch batch completed Triggers when a batch is completed. | **Field** | **Description** | | -------------- | --------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Limit** | Enter the maximum number of results to be worked with during one execution cycle. | ::: :::ExpandableHeading ## List batches Retrieves a list of batches. | **Field** | **Description** | | -------------- | --------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Limit** | Enter the maximum number of returned results (bundles). | ::: :::ExpandableHeading ## Get a batch Retrieves details of the specified batch. | **Field** | **Description** | | -------------- | --------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Batch ID** | Retrieves details of the specified batch. | ::: :::ExpandableHeading ## Create a batch Creates and executes a batch of API calls. | **Field** | **Description** | | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Input File ID** | Select a file to use as input to create a batch. | | **Endpoint** | Select the endpoint to use for all requests in the batch. Note that `/v1/embeddings` batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch. | ::: :::ExpandableHeading ## Cancel a batch Cancels an in-progress batch. The batch will be in status "cancelling" for up to 10 minutes before changing to "cancelled", where it will have partial results (if any) available in the output file. | **Field** | **Description** | | -------------- | --------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Batch ID** | Select a batch to cancel. | ::: # Other :::ExpandableHeading ## Transform text to structured data Identifies specified information in a prompt's raw text and returns it as structured data. | **Field** | **Description** | | ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **Model** | Select or map the model you want to use.
**Note**: Ensure you have access to the model you want to work with. Only models available for the account are listed for selection. | | **Text to Parse** | Enter the text containing the data that you want to transform. | | **Prompt** | Enter a short description explaining what type of data should be extracted from the text entered above. | | **Structured Data Definition** | Enter parameters or map the way in which the structured data should be returned.
* **Parameter Name**
Enter a name for the parameter. Adhere to the following rules:
1) The first character must be either a letter or an underscore. 2) Do not include any commas or spaces. 3) Do not use any special symbols, other than an underscore.
* **Description**
Enter a short description of the parameter. This description is part of the prompt, so the more clear your description, the more accurate the response.
For example, if you would like OpenAI to search for coordinates in the text, you can enter `Latitude and Longitude of the location`.
* **Data Type**
Select or map the data type format in which the parameter is returned.
If there will be multiple occurrences of similar data types, select an **Array** option. For example, if there are coordinates of multiple locations to be returned, select **Array (text)**.
* **Value Examples**
Enter or map examples of possible values to be returned. The more examples you provide, the more accurate the response will be.
* **Is Parameter Required?**
Select or map whether the parameter is required. When selecting `yes`, OpenAI will be forced to generate a value in the output, even if no value is detected in the text. | | **Object Definitions** | Enter object property details.
* **Parameter Name**
Enter a name for the object parameter. Adhere to the following rules:
1) The first character must be either a letter or an underscore. 2) Do not include any commas or spaces. 3) Do not use any special symbols, other than an underscore.
* **Description**
Enter a short description of the object parameter.
For example, if you would like OpenAI to search for coordinates in the text, you can enter `Latitude and Longitude of the location`.
* **Data Type**
Select or map the data type format in which the object parameter is returned.
If there will be multiple occurrences of similar data types, select an **Array** option. For example, if there are coordinates of multiple locations to be returned, select **Array (text)**.
* **Is Parameter Required?**
When selecting `yes`, OpenAI will be forced to generate a value in the output, even if no value is detected in the text. | ::: ::::ExpandableHeading ## Make an API call Performs an arbitrary authorized API call. :::hint{type="info"} For the list of available endpoints, see [OpenAI ChatGPT API Documentation](https://platform.openai.com/docs/api-reference/introduction). ::: | **Field** | **Description** | | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Connection** | [Create a connection to your OpenAI account.](docId\:BFy7nHwuWeTGFUEf-Zmop) | | **URL** | Enter a path relative to `https://api.openai.com`.
For example, `/v1/models`. | | **Method** | **GET**
to retrieve information for an entry.
**POST**
to create a new entry.
**PUT**
to update/replace an existing entry.
**PATCH**
to make a partial entry update.
**DELETE**
to delete an entry. | | **Headers** | Enter the desired request headers. You don't have to add authorization headers; we already did that for you. | | **Query String** | Enter the request query string. | | **Body** | Enter the body content for your API call. | ### Examples of Use - List Models The following API call returns all pages from your OpenAI account. **URL: **`/v1/models` **Method: **`GET` ::Image[]{src="https://api.archbee.com/api/optimize/oAyFj2GHlBeBVWF5OAir2/JGgHsZkMbN8b78ZhWIkbj_uuid-1ea05b35-4f5c-635a-7668-00b5d03ba463.png" size="76" width="645" height="829" position="center" darkWidth="645" darkHeight="829" showCaption="false"} The search matches can be found in the module's Output under **Bundle > Body > data**. In our example, 69 models were returned: ![](https://api.archbee.com/api/optimize/oAyFj2GHlBeBVWF5OAir2/ruFit-xhFLO9WBlgmWm5z_uuid-d167c437-1865-6946-247a-60ef03c00770.png "openai-4.png") ::::