OpenAI

Overview

OpenAI is the company behind the GPT, DALL-E, Whisper, and TTS models — some of the most advanced artificial intelligence models in the world. With the OpenAI integration in SquadOS, your agents can create chat completions, generate and edit images, transcribe audio, convert text to speech, generate embeddings, fine-tune models, manage assistants, threads, and vector stores for RAG, and much more.

Official website: https://openai.com/
Composio documentation: docs.composio.dev/toolkits/openai

Authentication

This tool uses an API key (API_KEY) to connect.

You will need the following fields:

Field	Required	Description
`api_key`	Yes	API key generated in the OpenAI dashboard, used to authenticate all requests.

How to get credentials

Go to platform.openai.com and log in or create an account.
In the side menu, click API keys.
Click Create new secret key, give it a name, and copy the generated value.
Store the key in a safe place — it will not be shown again.

How to connect in SquadOS

Go to Tools in the side menu (/admin/tools).
Open the Available tab and search for OpenAI.
Click the card to open the details and hit Connect.
You’re taken to the secure connection page hosted by Composio, where you enter the API key obtained above.
Once done, you’re sent back to SquadOS with the account connected and the tool available to agents. (Connection-flow details in Organization Tools.)

Available actions

Create Chat Completion

OPENAI_CREATE_CHAT_COMPLETION

Tool to create a chat completion response from OpenAI models. Use for conversational AI, text generation, function calling, multimodal tasks with vision/audio, and structured JSON outputs. Supports advanced features like reasoning models, tool use, and streaming responses.

Input parameters

Name	Type	Required	Description
`messages`	array	Yes	A list of messages comprising the conversation so far. Each message has a role and content.
`model`	string	Yes	ID of the model to use. Supported models include gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-3.5-turbo, o1, o1-mini, o3-mini, and others.
`n`	integer	No	How many chat completion choices to generate for each input message. Default is 1.
`temperature`	number	No	Sampling temperature between 0 and 2. Higher values like 0.8 make output more random, lower values like 0.2 make it more focused and deterministic. Mutually exclusive with top_p.
`tools`	array	No	A list of tools the model may call. Use this for function calling.
`response_format`	object	No	Response format specification for structured outputs.
`max_completion_tokens`	integer	No	An upper bound for the number of tokens that can be generated, including reasoning tokens. Preferred over max_tokens for newer models.
`stream`	boolean	No	If set to true, partial message deltas will be sent as server-sent events as they become available.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Response (Responses API)

OPENAI_CREATE_RESPONSE

Tool to generate a one-shot model response via the Responses API. Use for multimodal analysis (image + text), OCR/text extraction from images, or structured JSON outputs. For structured outputs, configure text.format with type=‘json_schema’ and your schema.

Input parameters

Name	Type	Required	Description
`input`	string	Yes	Input as a string for simple text prompts, or array of message objects for conversations or multimodal inputs with images.
`model`	string	Yes	Model to use for the response.
`tools`	array	No	List of tools the model can call. Supports function, code_interpreter, file_search, and web_search.
`temperature`	number	No	Sampling temperature between 0 and 2. Not supported with reasoning models.
`max_output_tokens`	integer	No	Maximum number of tokens the model can generate in the response.
`stream`	boolean	No	Whether to stream the response. Returns a stream of events during generation.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Generate Image

OPENAI_CREATE_IMAGE

Tool to generate an image via the OpenAI Images API and return hosted image asset URL and metadata. Use when you need to create images from text descriptions for single-shot image generation.

Input parameters

Name	Type	Required	Description
`prompt`	string	Yes	A text description of the desired image. Maximum length: 32000 characters for GPT image models, 4000 characters for dall-e-3, 1000 characters for dall-e-2.
`model`	string	Yes	ID of the model to use for image generation. Supported models include: ‘gpt-image-2’ (newest), ‘dall-e-3’, ‘dall-e-2’.
`size`	string	No	Size of the generated image. E.g., ‘1024x1024’, ‘1792x1024’.
`quality`	string	No	Quality of the image. Options: ‘standard’, ‘hd’, ‘auto’, ‘high’, ‘medium’, ‘low’.
`n`	integer	No	The number of images to generate. For dall-e-3, only n=1 is supported.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Edit Image

OPENAI_CREATE_IMAGE_EDIT

Tool to create edited or extended images via OpenAI Images Edit API. Use when you need to modify existing images based on a text prompt, with optional mask support for targeted edits.

Input parameters

Name	Type	Required	Description
`images`	array	Yes	Input image references to edit. For GPT image models, you can provide up to 16 images.
`prompt`	string	Yes	A text description of the desired image edit. Maximum 32000 characters.
`model`	string	No	The model to use for image editing. Supported models: ‘gpt-image-2’, ‘gpt-image-1.5’ (default), ‘dall-e-2’.
`size`	string	No	Requested output image size. Examples: ‘1024x1024’, ‘1024x1536’, ‘auto’.
`n`	integer	No	The number of edited images to generate. Default is 1.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Audio Transcription

OPENAI_CREATE_AUDIO_TRANSCRIPTION

Tool to transcribe audio files to text via OpenAI Audio Transcriptions API. Use when you need to convert speech in audio files to written text, optionally with timestamps or speaker diarization.

Input parameters

Name	Type	Required	Description
`model`	string	Yes	ID of the model to use for transcription. Options: ‘whisper-1’, ‘gpt-4o-transcribe’, ‘gpt-4o-mini-transcribe’.
`file`	object	No	Audio file to transcribe. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.
`language`	string	No	Language of the input audio in ISO-639-1 format (e.g., ‘en’ for English, ‘es’ for Spanish).
`response_format`	string	No	Format of the transcription output. Options: ‘json’, ‘text’, ‘srt’, ‘vtt’, ‘verbose_json’.
`temperature`	number	No	Sampling temperature between 0 and 1.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Speech (TTS)

OPENAI_CREATE_SPEECH

Tool to generate text-to-speech audio using OpenAI’s Audio API. Use when you need to convert text to natural-sounding speech with a choice of voices and models. Returns a hosted audio file URL with metadata, not raw bytes.

Input parameters

Name	Type	Required	Description
`input`	string	Yes	Text to convert to speech. Maximum 4096 characters.
`model`	string	Yes	TTS model to use. Options: ‘gpt-4o-mini-tts’, ‘tts-1’ (standard quality, faster), ‘tts-1-hd’ (high quality, slower).
`voice`	string	Yes	Voice to use for audio generation. Available voices: ‘alloy’, ‘ash’, ‘ballad’, ‘coral’, ‘echo’, ‘fable’, ‘onyx’, ‘nova’, ‘sage’, ‘shimmer’, ‘verse’.
`response_format`	string	No	Audio format for the output. Supported formats: ‘mp3’ (default), ‘opus’, ‘aac’, ‘flac’, ‘wav’, ‘pcm’.
`speed`	number	No	Playback speed of the audio. Range: 0.25 to 4.0. Default is 1.0.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Embeddings

OPENAI_CREATE_EMBEDDINGS

Tool to generate text embeddings via the OpenAI embeddings endpoint. Use for search, clustering, recommendations, and vector database storage workflows.

Input parameters

Name	Type	Required	Description
`input`	string	Yes	Input text to embed, encoded as a string or array of tokens. The input must not exceed the max input tokens for the model (8192 tokens for all embedding models).
`model`	string	Yes	ID of the model to use. Supported models include text-embedding-ada-002, text-embedding-3-small, and text-embedding-3-large.
`dimensions`	integer	No	The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.
`encoding_format`	string	No	The format to return the embeddings in. Can be either ‘float’ or ‘base64’. Defaults to ‘float’.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Moderation

OPENAI_CREATE_MODERATION

Tool to classify text and/or image inputs for potentially harmful content via the OpenAI Moderation API. Use for content safety checks, filtering user-generated content, or monitoring for policy violations across 13 harm categories including harassment, hate, violence, sexual content, self-harm, and illicit activities.

Input parameters

Name	Type	Required	Description
`input`	string	Yes	Input (or inputs) to classify. Can be a single string, an array of strings, or an array of multi-modal input objects with text and images.
`model`	string	No	The content moderation model to use. Options include: ‘omni-moderation-latest’ (default, supports text and images), ‘text-moderation-latest’ (text-only, latest version).

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Assistant

OPENAI_CREATE_ASSISTANT

Tool to create an OpenAI assistant. Use when you need to instantiate a new assistant with a specific model, instructions, tools, and tool resources. Required before creating threads and runs.

Input parameters

Name	Type	Required	Description
`model`	string	Yes	ID of the model to use.
`name`	string	No	The name of the assistant. The maximum length is 256 characters.
`instructions`	string	No	The system instructions that the assistant uses. The maximum length is 256,000 characters.
`tools`	array	No	A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant.
`description`	string	No	The description of the assistant. The maximum length is 512 characters.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Thread

OPENAI_CREATE_THREAD

Tool to create a new thread. Use when initializing a conversation with optional starter messages. Returns a thread_id that must be persisted and passed to all subsequent calls.

Input parameters

Name	Type	Required	Description
`messages`	array	No	Optional initial messages to start the thread with. Each message must include ‘role’ (‘user’ or ‘assistant’) and a non-empty string content.
`metadata`	object	No	Optional metadata key-value pairs to attach to the thread.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Message

OPENAI_CREATE_MESSAGE

Tool to create a message in a thread. Use to add user (or assistant) messages to an existing thread before creating a run.

Input parameters

Name	Type	Required	Description
`role`	string	Yes	The role of the entity creating the message. Allowed values: ‘user’ or ‘assistant’.
`content`	string	Yes	The content of the message. Can be a text string or an array of content parts.
`thread_id`	string	Yes	The ID of the thread to which this message belongs.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Run

OPENAI_CREATE_RUN

Tool to create a run on a thread with an assistant. Use when you need to execute an assistant to generate responses. Creating a message alone does not cause the assistant to respond; a run is the execution primitive.

Input parameters

Name	Type	Required	Description
`thread_id`	string	Yes	ID of the thread to run. A thread can only have one active run at a time.
`assistant_id`	string	Yes	ID of the assistant to use for this run.
`model`	string	No	Override the model used for this run.
`instructions`	string	No	Override the assistant’s instructions for this run.
`stream`	boolean	No	If true, returns a stream of events during the run.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Thread And Run

OPENAI_CREATE_THREAD_AND_RUN

Tool to create a thread and run it in one request. Use when you need to start a new conversation and immediately execute the assistant to generate a response. This is more efficient than calling create_thread and create_run separately.

Input parameters

Name	Type	Required	Description
`assistant_id`	string	Yes	ID of the assistant to use for this run.
`thread`	object	No	Parameters for creating a new thread.
`model`	string	No	Override the model used for this run.
`instructions`	string	No	Override the assistant’s instructions for this run.
`stream`	boolean	No	If true, returns a stream of events during the run as server-sent events.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

List Messages

OPENAI_LIST_MESSAGES

Tool to list messages from a thread. Use to retrieve all messages from a thread after a run completes, including the assistant’s replies.

Input parameters

Name	Type	Required	Description
`thread_id`	string	Yes	ID of the thread whose messages to list.
`limit`	integer	No	Limit on the number of messages to return (1–100). Default is 20.
`order`	string	No	Sort order by created_at timestamp: ‘asc’ for ascending, ‘desc’ for descending.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Retrieve Run

OPENAI_RETRIEVE_RUN

Tool to retrieve an Assistants run by ID to check status, errors, and usage. Use when polling run status until it reaches a terminal state (completed, failed, cancelled, incomplete, expired) before reading thread messages.

Input parameters

Name	Type	Required	Description
`run_id`	string	Yes	ID of the run to retrieve.
`thread_id`	string	Yes	ID of the thread that was run.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Submit Tool Outputs to Run

OPENAI_SUBMIT_TOOL_OUTPUTS_TO_RUN

Tool to submit tool call outputs to continue a run that requires action. Use when a run has status ‘requires_action’ and required_action.type is ‘submit_tool_outputs’. All tool outputs must be submitted together in a single request.

Input parameters

Name	Type	Required	Description
`run_id`	string	Yes	The ID of the run that requires the tool output submission.
`thread_id`	string	Yes	The ID of the thread to which this run belongs.
`tool_outputs`	array	Yes	A list of tools for which the outputs are being submitted. All tool outputs must be submitted in a single request.
`stream`	boolean	No	If true, returns a stream of events during the run execution after submitting tool outputs.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Vector Store

OPENAI_CREATE_VECTOR_STORE

Tool to create a new vector store. Use when you need to create a collection of processed files for file_search tools.

Input parameters

Name	Type	Required	Description
`name`	string	No	The name of the vector store. If not provided, the vector store will have no name.
`file_ids`	array	No	A list of File IDs that the vector store should use. Maximum 500 file IDs allowed.
`expires_after`	object	No	Expiration policy for a vector store.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Search Vector Store

OPENAI_SEARCH_VECTOR_STORE

Tool to search a vector store for relevant content. Use to retrieve text chunks semantically similar to the query for feeding context into LLM prompts.

Input parameters

Name	Type	Required	Description
`query`	string	Yes	Search query used to find relevant chunks in the vector store.
`vector_store_id`	string	Yes	The ID of the vector store to search.
`max_num_results`	integer	No	Maximum number of results to return. Default is 10.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Upload File

OPENAI_UPLOAD_FILE

Tool to upload a file for use across OpenAI endpoints. Use before referencing the file in tasks like fine-tuning. Returns a file_id that must be explicitly passed to endpoints like OPENAI_CREATE_ASSISTANT or OPENAI_CREATE_MESSAGE.

Input parameters

Name	Type	Required	Description
`file`	string	Yes	Binary content of the file to upload.
`purpose`	string	Yes	Intended purpose of the uploaded file. Currently only ‘fine-tune’ is supported.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

List Files

OPENAI_LIST_FILES

Tool to list files available in your OpenAI account. Use to verify uploads before referencing file_ids in other calls, or to identify files to delete in order to free up storage quota.

Input parameters

Name	Type	Required	Description
`purpose`	string	No	Filter by file purpose. E.g., ‘fine-tune’, ‘assistants’.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Fine-Tuning Job

OPENAI_CREATE_FINE_TUNING_JOB

Tool to create a fine-tuning job which begins the process of creating a new model from a given dataset. Use when you need to start fine-tuning a model with your training data.

Input parameters

Name	Type	Required	Description
`model`	string	Yes	The name of the model to fine-tune.
`training_file`	string	Yes	The ID of an uploaded file that contains training data. Your dataset must be formatted as a JSONL file and uploaded with the purpose ‘fine-tune’.
`validation_file`	string	No	The ID of an uploaded file that contains validation data.
`suffix`	string	No	A string of up to 64 characters that will be added to your fine-tuned model name.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

List Models

OPENAI_LIST_MODELS

Tool to list available models scoped to the current account/organization — some public models may be absent due to permissions. Use when you need to discover which models you can call.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Retrieve Model

OPENAI_RETRIEVE_MODEL

Tool to retrieve details of a specific model, confirming its metadata (ownership, created date) and verifying access under your org — a model appearing in OPENAI_LIST_MODELS does not guarantee access.

Input parameters

Name	Type	Required	Description
`model`	string	Yes	Identifier of the model to retrieve. Case-sensitive; use exact IDs as returned by OPENAI_LIST_MODELS.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Batch

OPENAI_CREATE_BATCH

Tool to create and execute a batch from an uploaded file of requests. Use after uploading a JSONL file with purpose ‘batch’ to process multiple API requests in a single batch operation.

Input parameters

Name	Type	Required	Description
`endpoint`	string	Yes	The endpoint to be used for all requests in the batch. Supported endpoints include /v1/responses, /v1/chat/completions, /v1/embeddings, /v1/completions, /v1/images/generations.
`input_file_id`	string	Yes	ID of an uploaded file containing requests for the batch. The file must be formatted as JSONL and uploaded with purpose ‘batch’.
`completion_window`	string	Yes	Time frame within which the batch should be processed. Currently only ‘24h’ is supported.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Create Audio Translation

OPENAI_CREATE_AUDIO_TRANSLATION

Tool to translate audio files to English text via OpenAI Audio Translations API. Use when you need to convert speech in audio files (any language) to English text.

Input parameters

Name	Type	Required	Description
`model`	string	Yes	ID of the model to use for translation. Only ‘whisper-1’ is currently available.
`file`	object	No	Audio file to translate to English. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.
`prompt`	string	No	Optional text to guide the model’s style. The prompt should be in English.
`response_format`	string	No	Format of the translation output. Options: ‘json’, ‘text’, ‘srt’, ‘vtt’, ‘verbose_json’.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Modify Assistant

OPENAI_MODIFY_ASSISTANT

Tool to modify an existing assistant. Use when you need to update an assistant’s configuration, model, instructions, tools, or metadata.

Input parameters

Name	Type	Required	Description
`assistant_id`	string	Yes	The ID of the assistant to modify.
`model`	string	No	ID of the model to use.
`name`	string	No	The name of the assistant. The maximum length is 256 characters.
`instructions`	string	No	The system instructions that the assistant uses. The maximum length is 256,000 characters.
`tools`	array	No	A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

Retrieve Assistant

OPENAI_RETRIEVE_ASSISTANT

Tool to retrieve details of a specific assistant. Use when you need to confirm assistant metadata before performing further operations. Prefer this over repeated OPENAI_CREATE_ASSISTANT calls to avoid cluttering assistant configurations.

Input parameters

Name	Type	Required	Description
`assistant_id`	string	Yes	Identifier of the assistant to retrieve. Must be a valid, stored OpenAI assistant ID.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.

List Assistants

OPENAI_LIST_ASSISTANTS

Tool to list assistants to discover the correct assistant_id by name or metadata. Use when assistant_id is unknown to avoid 404 errors.

Input parameters

Name	Type	Required	Description
`limit`	integer	No	Limit on the number of assistants to return (1-100). Default is 20.
`order`	string	No	Sort order by created_at timestamp: ‘asc’ for ascending, ‘desc’ for descending. Default is ‘desc’.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution.
`error`	string	No	Error if any occurred during the execution of the action.
`successful`	boolean	Yes	Whether or not the action execution was successful.