Skip to main content
OpenAI logo
  • Category: artificial intelligence
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 128
  • Triggers: 0
  • Slug: OPENAI
  • Version: 20261101_00
  • Instant: Supported on the latest version. Support varies by tool.

Tools

Slug: OPENAI_ADD_UPLOAD_PARTTool to add a part (chunk of bytes) to an Upload object. Use when uploading large files in chunks, with each part up to 64 MB.

Input Parameters

object
The chunk of bytes for this Part. Each Part can be at most 64 MB. Maximum total upload size is 8 GB across all parts. If not provided, use raw_content with raw_filename and raw_mimetype instead.
string
required
The ID of the Upload to add this Part to.
string
Base64-encoded file content or raw bytes to upload when FileUploadable is not available. Use this for inline data without needing an S3 key. Each Part can be at most 64 MB.
string
Filename for the inline content (e.g., ‘part1.txt’). Required when using raw_content.
string
MIME type for the inline content (e.g., ‘text/plain’, ‘application/octet-stream’). Defaults to ‘application/octet-stream’ if not provided.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CANCEL_BATCHTool to cancel an in-progress batch. Use when you need to stop a batch that is currently processing. The batch will be in status ‘cancelling’ for up to 10 minutes before changing to ‘cancelled’, where partial results (if any) will be available.

Input Parameters

string
required
The ID of the batch to cancel.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CANCEL_EVAL_RUNTool to cancel an ongoing evaluation run. Use when you need to stop an evaluation run that is currently in progress.

Input Parameters

string
required
The ID of the run to cancel
string
required
The ID of the evaluation whose run you want to cancel

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CANCEL_RESPONSETool to cancel a background model response by its ID. Use when you need to stop a response that was created with the ‘background’ parameter set to true. Only background responses can be cancelled; attempting to cancel a non-background response will fail.

Input Parameters

string
required
The ID of the response to cancel. Only responses created with the ‘background’ parameter set to true can be cancelled.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CANCEL_RUNRequest cancellation of an in-progress assistant run by thread and run ID, for example when the run is no longer needed. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses and Conversations APIs.

Input Parameters

string
required
ID of the run to cancel. The run must be in ‘in_progress’ status to be cancelled
string
required
ID of the thread to which this run belongs

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CANCEL_UPLOADTool to cancel an upload. Use when you need to stop an upload that is in progress. No parts may be added after cancellation.

Input Parameters

string
required
The ID of the Upload to cancel (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_COMPACT_RESPONSETool to compact a conversation or response to reduce token usage. Use when you need to reduce the size of long conversations while preserving important context. Either provide an array of input messages or reference a previous response ID to compact.

Input Parameters

array
Array of message objects to compact. Each message should have role, content array with type and text, and type field. Either input or previous_response_id is required.
string
required
Model ID to use for compaction (e.g., ‘gpt-4’, ‘gpt-5’, ‘o3-mini’)
string
Optional instructions for the compaction process
string
ID of a previous response to compact. Either input or previous_response_id is required.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_COMPLETE_UPLOADComplete a multipart Upload and create its usable File object.

Input Parameters

string
Optional MD5 checksum of the complete file contents.
array
required
The ordered list of upload Part IDs in final file order.
string
required
The ID of the Upload to complete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_AUDIO_TRANSCRIPTIONTranscribes audio files to text via the OpenAI Audio Transcriptions API, optionally returning timestamps.

Input Parameters

object
Audio file to transcribe. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm. If not provided, use raw_content with raw_filename and raw_mimetype instead.
string
required
ID of the model to use for transcription. Options: ‘whisper-1’, ‘gpt-4o-transcribe’, ‘gpt-4o-mini-transcribe’, ‘gpt-4o-mini-transcribe-2025-12-15’, ‘gpt-4o-transcribe-diarize’.
string
Optional text to guide the model’s style or continue a previous audio segment. The prompt should match the audio language. Supported by gpt-4o-transcribe and gpt-4o-mini-transcribe models.
string
Language of the input audio in ISO-639-1 format (e.g., ‘en’ for English, ‘es’ for Spanish). Providing the language can improve accuracy and speed.
string
Base64-encoded audio content or raw bytes to upload when FileUploadable is not available. Use this for inline audio data without needing an S3 key.
number
Sampling temperature between 0 and 1. Higher values (e.g., 0.8) make output more random, lower values (e.g., 0.2) make it more focused and deterministic.
string
Filename for the inline audio content (e.g., ‘audio.mp3’, ‘recording.wav’). Required when using raw_content.
string
MIME type for the inline audio content (e.g., ‘audio/mpeg’, ‘audio/wav’). Defaults to ‘audio/mpeg’ if not provided.
string ("json" | "text" | "srt" | "vtt" | "verbose_json")
Format of the transcription output. ‘json’ returns {text: ’…’}. ‘verbose_json’ includes task, language, duration, segments, and optionally words (with timestamp_granularities). ‘text’ returns plain text. ‘srt’ and ‘vtt’ return subtitle formats. whisper-1 supports all formats. gpt-4o-transcribe and gpt-4o-mini-transcribe support json or text only.
array
Timestamp granularities to include in the response. Use [‘word’] for word-level timestamps, [‘segment’] for segment-level, or both [‘word’, ‘segment’]. Only available when response_format is ‘verbose_json’.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_AUDIO_TRANSLATIONTool 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

object
Audio file to translate to English. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm. If not provided, use raw_content with raw_filename and raw_mimetype instead.
string
required
ID of the model to use for translation. Only ‘whisper-1’ (powered by Whisper V2 model) is currently available.
string
Optional text to guide the model’s style or continue a previous audio segment. The prompt should be in English.
string
Base64-encoded audio content or raw bytes to upload when FileUploadable is not available. Use this for inline audio data without needing an S3 key.
number
Sampling temperature between 0 and 1. Higher values (e.g., 0.8) make output more random, lower values (e.g., 0.2) make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
string
Filename for the inline audio content (e.g., ‘audio.mp3’, ‘recording.wav’). Required when using raw_content.
string
MIME type for the inline audio content (e.g., ‘audio/mpeg’, ‘audio/wav’). Defaults to ‘audio/mpeg’ if not provided.
string ("json" | "text" | "srt" | "vtt" | "verbose_json")
Format of the translation output. ‘json’ returns {text: ’…’}. ‘verbose_json’ includes task, language, duration, and text. ‘text’ returns plain text. ‘srt’ and ‘vtt’ return subtitle formats. Default is ‘json’.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_BATCHTool 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

string ("/v1/responses" | "/v1/chat/completions" | "/v1/embeddings" | "/v1/completions" | "/v1/moderations" | "/v1/images/generations" | "/v1/images/edits")
required
The endpoint to be used for all requests in the batch. Supported endpoints include /v1/responses, /v1/chat/completions, /v1/embeddings, /v1/completions, /v1/moderations, /v1/images/generations, and /v1/images/edits. Note that /v1/embeddings batches are restricted to a maximum of 50,000 embedding inputs across all requests.
object
Optional custom metadata for the batch. All values must be strings.
string
required
ID of an uploaded file containing requests for the batch. The file must be formatted as JSONL and uploaded with purpose ‘batch’. Can contain up to 50,000 requests and be up to 200 MB in size.
string ("24h")
required
Time frame within which the batch should be processed. Currently only ‘24h’ is supported.
object
Expiration policy for batch output and error files.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_CHAT_COMPLETIONCreates a chat completion from OpenAI models for conversational AI, text generation, function calling, vision or audio tasks, and structured JSON outputs. Supports reasoning models and tool use.

Input Parameters

integer
How many chat completion choices to generate for each input message. Default is 1
integer
If specified, the system will make a best effort to sample deterministically. Determinism is not guaranteed, check system_fingerprint in response
string
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence
string
A unique identifier representing your end-user. Helps OpenAI monitor and detect abuse
object
Parameters for audio output. Supported by audio-capable models
string
required
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
boolean
Whether to store the output of this chat completion request for use in model distillation or evaluations. Default is true for eligible models
array
A list of tools the model may call. Use this for function calling. The model can choose to call one or more functions
number
Nucleus sampling parameter. The model considers tokens with top_p probability mass. 0.1 means only tokens comprising the top 10% probability mass are considered. Mutually exclusive with temperature
boolean
If set to true, partial message deltas will be sent as server-sent events (SSE) as they become available
boolean
Whether to return log probabilities of the output tokens. If true, returns the log probabilities of each output token in the content
array
required
A list of messages comprising the conversation so far. Each message has a role and content
object
Developer-defined tags and values for filtering completions in the dashboard. All values must be strings
array
Deprecated. A list of functions the model may generate JSON inputs for. Use tools instead
object
Modify the likelihood of specified tokens appearing in the completion. Maps token IDs to bias values from -100 to 100. Use tokenizer to find token IDs
integer
The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model’s context length
array
Output modalities for the response. Include ‘audio’ for audio output. Defaults to [‘text’]
object
Configuration for predicted outputs. Used for latency optimization with certain models
number
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
string
Controls which tool is called by the model. ‘none’ means no tool calls, ‘auto’ lets the model decide, ‘required’ forces at least one tool call, or specify a particular tool/function
string ("auto" | "default")
Specifies the latency tier to use for processing the request. ‘auto’ lets the system infer the best tier, ‘default’ uses standard processing
integer
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. Requires logprobs=true
string
Deprecated. Controls which function is called by the model. Use tool_choice instead
object
Streaming options configuration.
object
Response format specification for structured outputs.
number
Number between -2.0 and 2.0. 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
string ("low" | "medium" | "high")
Reasoning effort level for reasoning models like o1. ‘low’ for faster responses, ‘high’ for more thorough reasoning. Only applicable to reasoning models
number
Number between -2.0 and 2.0. 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
boolean
Whether to enable parallel function calling during tool use. Default is true
integer
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. Preferred over max_tokens for newer models

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_COMPLETIONGenerate single-turn text completions using OpenAI’s legacy Completions API with an available compatible model.

Input Parameters

integer
How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop. Default is 1.
boolean
Echo back the prompt in addition to the completion. Default is false.
integer
If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.
string
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. Not supported with latest reasoning models o3 and o4-mini.
string
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
string
required
ID of the model to use. You can use the List models API to see all of your available models, or see the Model overview for descriptions of them. Examples: ‘gpt-3.5-turbo-instruct’, ‘davinci-002’, ‘babbage-002’.
number
An alternative to sampling with temperature, 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. We generally recommend altering this or temperature but not both. Default is 1.
string
required
The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.
boolean
Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Default is false.
string
The suffix that comes after a completion of inserted text. This parameter is only supported for gpt-3.5-turbo-instruct.
integer
Generates best_of completions server-side and returns the “best” (the one with the highest log probability per token). Results cannot be streamed. When used with n, best_of controls the number of candidate completions and n specifies how many to return. best_of must be greater than n. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.
integer
Include the log probabilities on the logprobs most likely output tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 5.
object
Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.
integer
The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model’s context length. Default is 16.
number
What sampling temperature to use, between 0 and 2. 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. Default is 1.
object
Options for streaming responses. Can include ‘include_usage’ and ‘include_obfuscation’ fields.
number
Number between -2.0 and 2.0. 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. Default is 0.
number
Number between -2.0 and 2.0. 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. Default is 0.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_CONTAINERTool to create a new container with configurable memory, expiration, file access, and network policies. Use when you need to provision an isolated execution environment.

Input Parameters

string
required
Name of the container to create.
array
Optional list of skills referenced by ID or provided as inline definitions.
array
Optional list of file IDs to copy to the container.
string ("1g" | "4g" | "16g" | "64g")
Memory limit options for the container.
object
Container expiration configuration.
string
Optional network access policy for the container. Can be ‘disabled’ to block all network access, or ‘allowlist’ to allow specific domains.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_CONTAINER_FILETool to create a file in a container. Use when adding files to an existing container either by referencing an uploaded file ID or by uploading raw file content directly.

Input Parameters

string
Binary content of the file to upload directly. Use this for multipart/form-data requests.
string
ID of an existing file to add to the container. Use this for JSON requests.
string
required
The ID of the container to create the file in

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_CONVERSATIONTool to create a new conversation for multi-turn interactions. Use when initializing a persistent conversation with optional starter messages.

Input Parameters

array
Optional initial items to start the conversation with. You may add up to 20 items at a time.
object
Optional metadata key-value pairs to attach to the conversation. Up to 16 pairs allowed, with keys ≤64 chars and values ≤512 chars.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_CONVERSATION_ITEMSTool to create items in a conversation with the given ID. Use when adding messages or other items to an existing conversation.

Input Parameters

array
required
The items to add to the conversation. You may add up to 20 items at a time
array
Additional fields to include in the response, such as item metadata or extended properties
string
required
The ID of the conversation to add items to

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_DECISIONEvaluate evidence with typed predicate, choice, and score questions. Each call costs at most $2.Instant: Supported on the latest version.Instant pricing: $0.10 per 1M input tokens ($0.20 long context); cache and output free; $2 max.

Input Parameters

string
required
Shared text evidence or ordered message and tool-call history evaluated by every question.
string
required
Decision model; gpt-6-luna is currently the only supported value.
array
required
One to 200 predicate, choice, or score questions answered in order.
string
Caller key used to partition prompt-cache reuse.
string
Opaque end-user abuse-detection identifier.
object
Prompt-cache mode and minimum lifetime.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_EMBEDDINGSTool to generate text embeddings via the OpenAI embeddings endpoint. Use for search, clustering, recommendations, and vector database storage workflows.

Input Parameters

string
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
string
required
Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for all embedding models), cannot be an empty string, and any array must be 2048 dimensions or less.
string
required
ID of the model to use. Supported models include text-embedding-ada-002, text-embedding-3-small, and text-embedding-3-large.
integer
The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models. Allows shortening embeddings without losing concept-representing properties.
string ("float" | "base64")
The format to return the embeddings in. Can be either ‘float’ or ‘base64’. Defaults to ‘float’.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_EVALTool to create an evaluation structure for testing a model’s performance. An evaluation is a set of testing criteria and data source config that dictates the schema of data used in the evaluation. Use when setting up automated testing for model outputs with graders like label_model, string_check, or text_similarity.

Input Parameters

string
required
Name of the evaluation for identification and organization
object
Optional metadata to attach to the evaluation for organizational purposes
array
required
A list of graders for all eval runs in this group. Graders can reference variables in the data source using double curly braces notation, like {{item.variable_name}}. To reference the model’s output, use the sample namespace (i.e., {{sample.output_text}}). Supported grader types: label_model, string_check, text_similarity, python, score_model
string
required
Configuration for the data source used for the evaluation runs. Dictates the schema of the data used in the evaluation. Options include ‘custom’ (with custom item_schema), ‘logs’ (from logged completions), or ‘stored_completions’ (from stored completion data)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_EVAL_RUNCreates an evaluation run for testing with a specified data source and model configuration. OpenAI has scheduled existing evals to become read-only on October 31, 2026, and the Evals API to shut down on November 30, 2026.

Input Parameters

string
Name of the evaluation run for identification
string
required
ID of the evaluation to create a run for
object
Optional metadata to attach to the run
string
required
Details about the run’s data source. Specifies the type (jsonl, completions, or responses) and the source of data (file_content with inline items or file_id)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_FINE_TUNING_JOBCreates a fine-tuning job from an uploaded training dataset and returns job details and status. Creation is restricted to eligible existing customers; OpenAI says active existing customers will no longer be able to create new jobs starting January 6, 2027.

Input Parameters

integer
The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed is not specified, one will be generated for you.
string
required
The name of the model to fine-tune. You can select one of the supported models for fine-tuning.
object
The method used for fine-tuning. Must include a ‘type’ field set to ‘supervised’, ‘dpo’, or ‘reinforcement’. Can include method-specific configuration under corresponding keys (‘supervised’, ‘dpo’, or ‘reinforcement’).
string
A string of up to 64 characters that will be added to your fine-tuned model name. For example, a suffix of ‘custom-model-name’ would produce a model name like ‘ft:gpt-4o-mini:openai:custom-model-name:7p4lURel’.
object
Set of 16 key-value pairs that can be attached to the fine-tuning job. This can be useful for storing additional information about the job in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.
array
A list of integrations to enable for your fine-tuning job. Each integration must specify ‘type’ and ‘wandb’ configuration.
string
required
The ID of an uploaded file that contains training data. See upload file for how to upload a file. Your dataset must be formatted as a JSONL file and uploaded with the purpose ‘fine-tune’.
object
The hyperparameters used for the fine-tuning job. This value is now deprecated in favor of ‘method’, and should be passed in under the ‘method’ parameter. Can include ‘batch_size’, ‘learning_rate_multiplier’, and ‘n_epochs’. Each can be either ‘auto’ (string) or a specific number.
string
The ID of an uploaded file that contains validation data. If provided, the data is used to generate validation metrics periodically during fine-tuning. The same data should not be present in both train and validation files. Your dataset must be formatted as a JSONL file and uploaded with the purpose ‘fine-tune’.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_IMAGETool 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

integer
The number of images to generate. For dall-e-3, only n=1 is supported. For dall-e-2, you can request up to 10 images.
string
Size of the generated image. For gpt-image-2: any resolution ‘WxH’ where both edges are multiples of 16, max edge 3840px, 655,360-8,294,400 total pixels, max 3:1 aspect ratio (e.g., ‘1024x1024’, ‘2048x2048’, ‘3840x2160’), or ‘auto’ (default). For gpt-image-1: ‘1024x1024’, ‘1536x1024’ (landscape), ‘1024x1536’ (portrait), or ‘auto’ (default). For dall-e-3: ‘1024x1024’, ‘1792x1024’, ‘1024x1792’. For dall-e-2: ‘256x256’, ‘512x512’, ‘1024x1024’.
string
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
string
required
ID of the model to use for image generation. Supported models include: ‘gpt-image-2’ (newest, state-of-the-art, flexible sizes, png/jpeg/webp output), ‘gpt-image-1’, ‘gpt-image-1-mini’, ‘gpt-image-1.5’, ‘chatgpt-image-latest’, ‘dall-e-3’, ‘dall-e-2’. Note: DALL-E 2 and DALL-E 3 are deprecated and will stop being supported on 05/12/2026.
string ("vivid" | "natural")
The style of the generated image. ‘vivid’ causes the model to lean towards generating hyper-real and dramatic images. ‘natural’ causes the model to produce more natural, less hyper-real looking images. Only supported for dall-e-3.
string
required
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.
string ("standard" | "hd" | "auto" | "high" | "medium" | "low")
Quality values for image generation across different models.
string ("transparent" | "opaque" | "auto")
Background transparency setting for the generated image. Only supported for GPT image models. ‘transparent’ creates images with transparent backgrounds, ‘opaque’ creates fully opaque backgrounds, ‘auto’ (default) lets the model decide. Note: gpt-image-2 does NOT support ‘transparent’ — requests will be transformed to ‘auto’ with an execution message.
string ("auto" | "low")
Content moderation strictness. ‘auto’ (default) applies standard filtering, ‘low’ applies less restrictive filtering. Supported by gpt-image-2 and gpt-image-1 series. Ignored for dall-e models.
string ("png" | "jpeg" | "webp")
Output image format. Supported by gpt-image-2 (png/jpeg/webp) and gpt-image-1 series (png/jpeg/webp). Defaults to ‘png’. Ignored for dall-e models.
integer
Compression level (0-100) for jpeg and webp output formats. Higher values preserve more detail. Only applies when output_format is ‘jpeg’ or ‘webp’. Supported by gpt-image-2 and gpt-image-1 series.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_IMAGE_EDITTool 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

integer
The number of edited images to generate. Default is 1. The exact upper limit may vary by model.
object
Reference an input image by either URL or uploaded file ID.
string
Requested output image size. Examples: ‘1024x1024’, ‘1024x1536’, ‘1536x1024’, ‘auto’. Default is ‘auto’, which automatically determines the best size.
string
A unique identifier representing your end-user, which can help OpenAI monitor and detect abuse.
string
The model to use for image editing. Supported models: ‘gpt-image-2’ (newest, flexible sizes, png/jpeg/webp output), ‘gpt-image-1.5’ (default), ‘gpt-image-1’, ‘gpt-image-1-mini’, ‘chatgpt-image-latest’, ‘dall-e-2’. Note: JSON edits support GPT image models only; DALL-E edits require multipart format. gpt-image-2 does NOT support ‘transparent’ background — requests will be transformed to ‘auto’.
array
required
Input image references to edit. For GPT image models, you can provide up to 16 images. Each image reference must provide either ‘image_url’ or ‘file_id’, not both.
string
required
A text description of the desired image edit. Describes what changes should be made to the input image(s). Maximum 32000 characters.
string ("auto" | "high" | "medium" | "low")
Quality values for image editing.
string ("auto" | "transparent" | "opaque")
Background behavior for generated image output.
string
Moderation level for GPT image models. Default is ‘auto’. Controls content moderation strictness.
string ("png" | "webp" | "jpeg")
Output image format.
string
Controls fidelity to the original input image(s). Higher fidelity preserves more of the original image characteristics.
integer
Compression level for ‘jpeg’ or ‘webp’ output. Range: 0-100. Higher values mean better quality but larger file sizes.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_IMAGE_VARIATIONCreate alternative versions of an existing square PNG image using the legacy image variations operation, with options for count, size, and response format. DEPRECATED: Its documented model, DALL-E 2, shut down on May 12, 2026; OpenAI recommends GPT Image models as replacements.

Input Parameters

integer
The number of images to generate. Must be between 1 and 10. Defaults to 1.
string ("256x256" | "512x512" | "1024x1024")
Size options for image variations with dall-e-2.
string
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
object
required
The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.
string
The model to use for image generation. Only ‘dall-e-2’ is supported at this time. Defaults to ‘dall-e-2’ if not specified.
string ("url" | "b64_json")
Format of the response for image generation.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_MESSAGECreate a message in an Assistants conversation thread. This adds the message without triggering a model response; a separate run was needed for an assistant reply. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string ("user" | "assistant")
required
REQUIRED. Role of the message sender: ‘user’ or ‘assistant’. Use ‘user’ for user-generated messages, ‘assistant’ for assistant-generated messages. Example: {‘thread_id’: ‘thread_abc123’, ‘role’: ‘user’, ‘content’: ‘Hello’}
string
required
Message content as a string or list of structured parts Must be non-empty; empty or missing content causes the request to fail.
object
Up to 16 key-value pairs of metadata (keys ≤64 chars, values ≤512 chars)
string
required
ID of the thread to create the message in Must be from a prior OPENAI_CREATE_THREAD call; incorrect IDs route messages to wrong threads or cause errors.
array
Optional files to attach to the message Each entry requires a valid file_id (from OPENAI_UPLOAD_FILE) and a recognized tool name; missing or unknown tool names cause validation failures.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_MODERATIONTool 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

string
required
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. For multi-modal inputs, each object should have ‘type’ (‘text’ or ‘image_url’) and corresponding content fields.
string
The content moderation model to use. Options include: ‘omni-moderation-latest’ (default, supports text and images), ‘omni-moderation-2024-09-26’ (specific omni version), ‘text-moderation-latest’ (text-only, latest version), ‘text-moderation-stable’ (text-only, stable version), ‘text-moderation-007’ (text-only, legacy version). Learn more in the moderation guide and available models documentation.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_REALTIME_CALLCreates a Realtime API call over WebRTC and returns the SDP answer needed to complete the peer connection. A call ID is returned when it can be extracted from the Location header.

Input Parameters

string
required
WebRTC Session Description Protocol (SDP) offer generated by the caller. This must be a complete SDP offer with media descriptions (audio), ICE parameters, fingerprints, and other WebRTC connection details. The SDP establishes the peer connection parameters.
string
required
The Realtime model to use for the call. Example: ‘gpt-4o-realtime-preview-2024-12-17’. This model handles bidirectional audio streaming and data channel messaging over WebRTC.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_REALTIME_CLIENT_SECRETTool to create an ephemeral client secret for authenticating Realtime API connections. Use when you need to establish a WebSocket connection to OpenAI’s Realtime API for voice or streaming interactions.

Input Parameters

string
Session configuration. Choose either a realtime session (type=‘realtime’) or a transcription session (type=‘transcription’). If not provided, defaults to a basic realtime session
object
Configuration for the client secret expiration.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_REALTIME_SESSIONTool to create an ephemeral API token for client-side Realtime API applications. Use when setting up browser-based real-time audio/text interactions.

Input Parameters

string
required
Model to use for the realtime session
number
The speed of the model’s spoken response. 1.0 is default, 0.25 is minimum, 1.5 is maximum
array
Tools (functions) available to the model
string
A built-in voice name or a custom voice reference
object
Prompt configuration.
string
Configuration options for tracing. Set to null to disable. ‘auto’ creates a trace with default values
array
The set of modalities the model can respond with. To disable audio, set this to [‘text’]
string
Truncation configuration. Controls how conversation is truncated when exceeding token limits
number
Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8
string
How the model chooses tools. Options are ‘auto’, ‘none’, ‘required’, or specify a function
string
System instructions for the model. Guides the model on desired responses and behavior
object
Configuration for turn detection (server VAD).
string ("pcm16" | "g711_ulaw" | "g711_alaw")
The format of input audio
string ("pcm16" | "g711_ulaw" | "g711_alaw")
The format of output audio
object
Configuration for input audio transcription.
string
Maximum number of output tokens for a single assistant response. Provide an integer between 1 and 4096, or ‘inf’ for maximum available

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_REALTIME_TRANSCRIPTION_SESSIONTool to create an ephemeral API token for realtime transcriptions via the Realtime API. Use when you need to authenticate browser clients for realtime audio transcription sessions. Returns a session object with a client_secret containing a usable ephemeral API token.

Input Parameters

array
The set of items to include in the transcription. Current available items are: ‘item.input_audio_transcription.logprobs’
object
Configuration for turn detection.
string ("pcm16" | "g711_ulaw" | "g711_alaw")
Format of input audio for realtime transcription.
object
Configuration for input audio transcription.
object
Configuration for input audio noise reduction.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_RESPONSECreates a model response via the Responses API for text or image analysis and structured JSON output. Returns selected response fields including the ID and output array; aggregated output text may be absent.

Input Parameters

object
Text output configuration.
string
required
Input as a string for simple text prompts, or array of message objects for conversations or multimodal inputs with images
string
required
Model to use for the response
boolean
Whether to store the response for model distillation and training. Set to false to opt out
array
List of tools the model can call. Supports function, code_interpreter, file_search, and web_search
number
Nucleus sampling parameter. Alternative to temperature. Not supported with reasoning models
boolean
Whether to stream the response. Returns a stream of events during generation
object
Optional metadata to attach to the response. All values must be strings
object
Reasoning configuration for reasoning models.
boolean
Whether to run the model response in the background. When set to true, the response is created asynchronously and can be polled for completion. Only background responses can be cancelled
array
Output modalities. Include ‘audio’ for audio output. Defaults to [‘text’]
number
Sampling temperature between 0 and 2. Higher values (e.g., 0.8) make output more random, lower values (e.g., 0.2) more focused. Not supported with reasoning models
string
Controls which tool is called. ‘auto’ lets model decide, ‘none’ disables tools, ‘required’ forces a tool call, or specify a particular function
integer
Maximum number of tokens the model can generate in the response
boolean
Whether to enable parallel function calling. Default is true

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_RUNCreate an assistant run on an existing thread to execute the assistant and generate responses, optionally adding messages and setting run options. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses and Conversations APIs.

Input Parameters

string
Override the model used for this run. If not specified, uses the assistant’s model
array
Override the tools the assistant can use for this run
number
Nucleus sampling parameter. Alternative to temperature
boolean
If true, returns a stream of events during the run
object
Up to 16 key-value pairs of metadata (keys ≤64 chars, values ≤512 chars)
string
required
ID of the thread to run. Note: A thread can only have one active run at a time. If a run is already active (status: queued, in_progress, requires_action, or cancelling), wait for it to complete or cancel it before creating a new run.
number
Sampling temperature between 0 and 2. Higher values make output more random
string
Controls which tool is called. Can be ‘none’, ‘auto’, ‘required’, or a specific tool object
string
required
ID of the assistant to use for this run
string
Override the assistant’s instructions for this run
string
Format for the model’s output. Can be ‘auto’ or an object specifying the format
string
Reasoning effort level for reasoning models (e.g., ‘low’, ‘medium’, ‘high’)
integer
Maximum number of prompt tokens to use for the run
array
Additional messages to add to the thread before creating the run
boolean
Whether to enable parallel function calling during tool use. Default is true
object
Controls how the thread will be truncated prior to the run.
integer
Maximum number of completion tokens that can be generated
string
Additional instructions to append to the assistant’s instructions

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_SKILLTool to create a skill from uploaded files. Use when you need to create a new skill with SKILL.md and supporting files.

Input Parameters

array
required
List of files to upload for the skill. Must include at least a SKILL.md file. The SKILL.md file should contain frontmatter with name and description.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_SPEECHTool 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

string
required
Text to convert to speech. Maximum 4096 characters. The text will be spoken by the selected voice using the chosen model.
string ("gpt-4o-mini-tts" | "tts-1" | "tts-1-hd")
required
TTS model to use for audio generation. Options: ‘gpt-4o-mini-tts’ (GPT-4o mini TTS model), ‘tts-1’ (standard quality, faster), ‘tts-1-hd’ (high quality, slower).
number
Playback speed of the audio. Range: 0.25 to 4.0. Default is 1.0. Values < 1.0 slow down speech, > 1.0 speed it up.
string ("alloy" | "ash" | "ballad" | "coral" | "echo" | "fable" | "onyx" | "nova" | "sage" | "shimmer" | "verse")
required
Voice to use for audio generation. Available voices: ‘alloy’, ‘ash’, ‘ballad’, ‘coral’, ‘echo’, ‘fable’, ‘onyx’, ‘nova’, ‘sage’, ‘shimmer’, ‘verse’. Each voice has a distinct tone and personality.
string ("mp3" | "opus" | "aac" | "flac" | "wav" | "pcm")
Audio format for the output. Supported formats: ‘mp3’ (default, widely compatible), ‘opus’ (low latency streaming), ‘aac’ (digital audio compression), ‘flac’ (lossless), ‘wav’ (uncompressed), ‘pcm’ (raw 16-bit PCM audio at 24kHz).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_THREADCreate an Assistants API conversation thread with optional starter messages and metadata. The thread ID identifies the conversation for subsequent operations. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

array
Optional initial messages to start the thread with Each message must include role (‘user’ or ‘assistant’) and a non-empty string content; missing or invalid values will reject the request.
object
Optional metadata key-value pairs to attach to the thread Keys and values must be short strings; nested objects or large payloads are rejected.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_THREAD_AND_RUNCreate an Assistants thread and run in one request to start a conversation and execute an assistant. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses and Conversations APIs.

Input Parameters

string
Override the model used for this run. If not specified, uses the assistant’s model
array
Override the tools the assistant can use for this run (max 20 tools)
number
Nucleus sampling parameter (top_p). Alternative to temperature. Default is 1
boolean
If true, returns a stream of events during the run as server-sent events
object
Parameters for creating a new thread.
object
Up to 16 key-value pairs of metadata (keys ≤64 chars, values ≤512 chars)
number
Sampling temperature between 0 and 2. Higher values make output more random. Default is 1
string
Controls which tool is called. Can be ‘none’, ‘auto’, ‘required’, or a specific tool object
string
required
ID of the assistant to use for this run
string
Override the assistant’s instructions for this run
object
Tool resources for the run.
string
Format for the model’s output. Can be ‘auto’ or an object specifying the format
integer
Maximum number of prompt tokens to use for the run (minimum 256)
boolean
Whether to enable parallel function calling during tool use. Default is true
object
Controls how the thread will be truncated prior to the run.
integer
Maximum number of completion tokens that can be generated (minimum 256)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_UPLOADTool to create an intermediate Upload object for large file uploads. Use when uploading files larger than the direct upload limit by adding Parts to the Upload. The Upload accepts up to 8 GB total and expires after one hour if not completed.

Input Parameters

integer
required
The total number of bytes in the file you are uploading. Maximum 8 GB (8589934592 bytes)
string ("assistants" | "batch" | "fine-tune" | "vision")
required
The intended purpose of the uploaded file. Must be one of: ‘assistants’, ‘batch’, ‘fine-tune’, or ‘vision’
string
required
The name of the file to upload
string
required
The MIME type of the file. This must fall within the supported MIME types for your file purpose
object
Expiration policy for a file.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_VECTOR_STORETool to create a new vector store. Use when you need to create a collection of processed files for file_search tools.

Input Parameters

string
The name of the vector store. If not provided, the vector store will have no name.
array
A list of File IDs that the vector store should use. Useful for tools like file_search that can access files. Maximum 500 file IDs allowed.
object
Set of up to 16 key-value pairs that can be attached to the vector store. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.
object
Expiration policy for a vector store.
string
The chunking strategy used to chunk the file(s). If not set, will use the ‘auto’ strategy. Only applicable if file_ids is non-empty.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_VECTOR_STORE_FILETool to create a vector store file by attaching a File to a vector store. Use when you need to add files to a vector store for file search capabilities.

Input Parameters

string
required
A File ID that the vector store should use. Useful for tools like file_search that can access files.
string
required
The ID of the vector store for which to create a File.
string
The chunking strategy used to chunk the file(s). If not set, will use the ‘auto’ strategy. Can be either ‘auto’ or ‘static’.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_VECTOR_STORE_FILE_BATCHTool to create a vector store file batch. Use when attaching multiple files to a vector store for file search capabilities.

Input Parameters

array
A list of objects that each include a file_id plus optional attributes or chunking_strategy. Use this when you need to override metadata for specific files. The global attributes or chunking_strategy will be ignored and must be specified for each file. Mutually exclusive with ‘file_ids’.
array
A list of File IDs that the vector store should use. Useful for tools like file_search that can access files. If attributes or chunking_strategy are provided at the top level, they will be applied to all files in the batch. Mutually exclusive with ‘files’.
object
Optional metadata attributes to apply to all files in the batch. All values must be strings. Ignored if ‘files’ is provided instead of ‘file_ids’.
string
required
The ID of the vector store for which to create a file batch.
string
The chunking strategy used to chunk the file(s). If not set, will use the ‘auto’ strategy. Applies to all files if ‘file_ids’ is used. Ignored if ‘files’ is provided.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_VIDEOCreate an asynchronous video generation job from a text prompt using the OpenAI Videos API; the job ID and status were used to track generation. DEPRECATED: The Videos API was shut down on September 24, 2026.

Input Parameters

string ("720x1280" | "1280x720" | "1024x1792" | "1792x1024")
Resolution options for video generation.
string
ID of the Sora model to use for video generation. If not specified, the default model will be used. Common models include ‘veo-2.0’ and other Sora variants.
string
required
Text prompt that describes the video to generate. The prompt guides the visual content, scene composition, motion, and style of the video. Maximum length: 32000 characters.
string ("4" | "8" | "12")
Duration options for video generation.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_CREATE_VIDEO_REMIXSubmit a remix job for an existing generated video using a new prompt. OpenAI’s Videos API was shut down on September 24, 2026.

Input Parameters

string
required
Updated text prompt that directs the remix generation. Describes the transformations or changes to apply to the original video.
string
required
The identifier of the completed video to remix. Must be a valid video ID from a previously generated video.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_ASSISTANTDelete a specific Assistants API assistant by ID. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
required
Identifier of the assistant to delete (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_CHAT_COMPLETIONTool to delete a stored chat completion by its ID. Use when you need to remove a chat completion that was created with store=true.

Input Parameters

string
required
The ID of the chat completion to delete. Only chat completions created with store=true can be deleted.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_CONTAINERTool to delete a specific container by its ID. Use when you need to remove a container after confirming its ID.

Input Parameters

string
required
The ID of the container to delete (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_CONTAINER_FILETool to delete a file from a container. Use when you need to remove a file from a specific container by providing both container ID and file ID.

Input Parameters

string
required
ID of the file to delete from the container (path parameter)
string
required
ID of the container containing the file (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_CONVERSATIONTool to delete a conversation by its ID. Items in the conversation will not be deleted. Use when you need to remove a conversation.

Input Parameters

string
required
The ID of the conversation to delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_CONVERSATION_ITEMTool to delete an item from a conversation with the given IDs. Use when you need to remove a specific message or item from a conversation.

Input Parameters

string
required
The ID of the item to delete
string
required
The ID of the conversation that contains the item

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_EVALTool to delete a specific evaluation by its ID. Use when you need to remove an evaluation after confirming its ID.

Input Parameters

string
required
The ID of the evaluation to delete (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_EVAL_RUNDeletes a specific evaluation run. OpenAI has scheduled existing evals to become read-only on October 31, 2026, and the Evals API to shut down on November 30, 2026.

Input Parameters

string
required
The ID of the run to delete
string
required
The ID of the evaluation to delete the run from

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_FILEDeletes a file by its ID. Confirm the target before deleting it; removing unneeded files can help manage storage quotas.

Input Parameters

string
required
ID of the file to delete (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_MESSAGEDelete a specific message from an Assistants conversation thread using the thread and message IDs. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
required
The ID of the thread to which this message belongs.
string
required
The ID of the message to delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_RESPONSETool to delete a model response with the given ID. Use when you need to remove a stored response from the Responses API.

Input Parameters

string
required
The ID of the response to delete (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_SKILLTool to delete a specific skill by its ID. Use when you need to remove a skill after confirming its ID.

Input Parameters

string
required
The identifier of the skill to delete (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_THREADDelete an Assistants API conversation thread by its ID. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
required
The ID of the thread to delete (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_VECTOR_STORETool to delete a vector store. Use when you need to permanently remove a vector store by its ID.

Input Parameters

string
required
The ID of the vector store to delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_VECTOR_STORE_FILETool to delete a vector store file. This removes the file from the vector store but does not delete the file itself. Use when you need to remove a file from a vector store’s search index.

Input Parameters

string
required
The ID of the file to delete from the vector store.
string
required
The ID of the vector store that the file belongs to.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DELETE_VIDEODelete a video by ID from OpenAI’s Videos API, returning a deletion result. DEPRECATED: The Videos API shut down on September 24, 2026; OpenAI does not list a replacement for it.

Input Parameters

string
required
The identifier of the video to delete (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DOWNLOAD_FILETool to download the contents of a specified file by its ID. Use when you need to retrieve file content from OpenAI.

Input Parameters

string
required
The ID of the file to use for this request.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_DOWNLOAD_VIDEODownload a generated video’s MP4 content or its thumbnail or spritesheet by video ID. DEPRECATED: OpenAI’s Videos API shut down on September 24, 2026; OpenAI does not list a replacement for it.

Input Parameters

string ("video" | "thumbnail" | "spritesheet")
Which downloadable asset to return. Options: ‘video’ (default, MP4 video file), ‘thumbnail’ (preview thumbnail image), ‘spritesheet’ (sprite sheet for preview scrubbing).
string
required
The identifier of the video whose media to download.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_CHAT_COMPLETIONTool to retrieve a stored chat completion. Use when you need to fetch a previously created chat completion that was stored with store=true.

Input Parameters

string
required
The ID of the chat completion to retrieve. Only completions created with store=true can be retrieved

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_CHAT_COMPLETION_MESSAGESTool to retrieve messages from a stored chat completion. Use when you need to fetch the conversation history of a previously created chat completion. Only works with completions that were created with the store parameter set to true.

Input Parameters

string
Identifier for the last message from the previous pagination request. Use to fetch the next page of results
integer
Number of messages to retrieve. Default is 20
string ("asc" | "desc")
Sort order for messages by timestamp.
string
required
The ID of the chat completion to retrieve messages from. Only completions created with store=true will be retrievable

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_CHATKIT_THREADTool to retrieve a ChatKit thread by its ID. Use when you need to fetch details about a specific ChatKit thread including its status, title, and owner.

Input Parameters

string
required
Identifier of the ChatKit thread to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_CONVERSATION_ITEMTool to retrieve a single item from a conversation. Use when you need to fetch details of a specific message or item within a conversation.

Input Parameters

array
Additional fields to include in the response, such as item metadata or extended properties
string
required
The ID of the item to retrieve
string
required
The ID of the conversation that contains the item

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_EVALTool to retrieve an evaluation by ID. Use when you need to inspect an existing evaluation’s configuration, data source settings, or testing criteria.

Input Parameters

string
required
The ID of the evaluation to retrieve

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_EVAL_RUNTool to retrieve an evaluation run by ID to check status and results. Use when you need to monitor an evaluation run’s progress or retrieve its final results after creation.

Input Parameters

string
required
ID of the run to retrieve
string
required
ID of the evaluation to retrieve runs for

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_EVAL_RUN_OUTPUT_ITEMTool to retrieve a specific output item from an evaluation run by its ID. Use when you need detailed results for a particular test case within an evaluation run.

Input Parameters

string
required
The ID of the run to retrieve
string
required
The ID of the evaluation to retrieve runs for
string
required
The ID of the output item to retrieve

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_EVAL_RUN_OUTPUT_ITEMSTool to get a list of output items for an evaluation run. Use when you need to retrieve the detailed results of an eval run, including grading outcomes, input/output samples, and token usage.

Input Parameters

string
Identifier for the last output item from the previous pagination request
integer
Number of output items to retrieve
string ("asc" | "desc")
Sort order for output items.
string
required
The ID of the run to retrieve output items for
string ("fail" | "pass")
Status filter for output items.
string
required
The ID of the evaluation to retrieve runs for

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_EVAL_RUNSTool to get a paginated list of runs for an evaluation. Use when you need to retrieve all runs or check the status of multiple runs for a specific evaluation.

Input Parameters

string
Identifier for the last run from the previous pagination request. Use this to fetch the next page of results.
integer
Number of runs to retrieve. Default is 20.
string ("asc" | "desc")
Sort order for evaluation runs.
string ("queued" | "in_progress" | "completed" | "canceled" | "failed")
Status filter for evaluation runs.
string
required
The ID of the evaluation to retrieve runs for

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_INPUT_TOKEN_COUNTSTool to calculate input token counts for OpenAI API requests. Use when you need to estimate token usage before making an API call, validate content fits within model limits, or optimize prompts for token efficiency.

Input Parameters

object
Configuration for text output formatting.
string
Input content to count tokens for. Can be a simple text string or a structured object. Use this for single input token counting
string
ID of the model to use for token counting. Required for accurate token counts. Examples: ‘gpt-4o-mini’, ‘gpt-4o’, ‘gpt-4-turbo’, ‘gpt-3.5-turbo’. Different models may use different tokenization, so specify the model you plan to use
array
List of tools/functions available to the model. Include this if you’re using function calling to get accurate token counts
object
Configuration for reasoning parameters.
string ("auto" | "disabled")
Truncation mode for input content.
object
Tool choice configuration. Include when using specific tool selection strategies
object
Conversation object to count tokens for. Use when counting tokens for a full conversation context
string
System instructions or prompts to include in token count. Use when you need to account for instruction tokens in the total count
boolean
Whether to enable parallel tool calling. Affects token count when using multiple tools
string
ID of a previous response to include in the context for token counting

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_MESSAGERetrieve a specific message from an Assistants thread by thread and message IDs to inspect its content and details. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
required
The ID of the thread to which this message belongs
string
required
The ID of the message to retrieve

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_RESPONSETool to retrieve a model response by ID. Use when you need to check the status, output, or metadata of a previously created response.

Input Parameters

boolean
If true, the model response data will be streamed using server-sent events. See OpenAI Streaming documentation for details
array
Additional fields to include in the response (e.g., conversation details or other metadata)
string
required
The ID of the response to retrieve
integer
The sequence number of the event after which to start streaming (only applicable when stream=true)
boolean
When true, stream obfuscation adds random characters to normalize payload sizes for security. Set to false to optimize bandwidth if network is trusted. Only applies to streaming

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_RUN_STEPRetrieve a specific Assistants run step by thread, run, and step ID to inspect execution progress, tool calls, or message creation. File search result content can be requested. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
required
The ID of the run to which the run step belongs.
array
Additional fields to include in the response. Use ‘step_details.tool_calls[].file_search.results[].content’ to include file search result content.
string
required
The ID of the run step to retrieve.
string
required
The ID of the thread to which the run and run step belongs.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_VECTOR_STORETool to retrieve a vector store by its ID. Use when you need to get details of an existing vector store for file_search operations.

Input Parameters

string
required
The ID of the vector store to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_VECTOR_STORE_FILETool to retrieve a file from a vector store. Use when you need to check the status or details of a file attached to a vector store.

Input Parameters

string
required
The ID of the file being retrieved.
string
required
The ID of the vector store that the file belongs to.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_VECTOR_STORE_FILE_BATCHRetrieve a file batch by its vector store and batch IDs to check the status and file counts of a batch processing operation.

Input Parameters

string
required
The ID of the file batch being retrieved.
string
required
The ID of the vector store that the file batch belongs to.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_GET_VIDEORetrieve a video generation job by ID to inspect its status, progress, and details. DEPRECATED: OpenAI’s Videos API was shut down on September 24, 2026.

Input Parameters

string
required
The unique identifier of the video generation job to retrieve. This ID is returned when you create a video generation job.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_ASSISTANTSList Assistants API assistants to discover an assistant ID from returned names or metadata. Results support cursor pagination, creation-time ordering, and page sizes of 1–100. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
Cursor for pagination. Provide an object ID to fetch the next page after that ID.
integer
Limit on the number of assistants to return (1-100). Default is 20.
string ("asc" | "desc")
Sort order by created_at timestamp: ‘asc’ for ascending, ‘desc’ for descending. Default is ‘desc’.
string
Cursor for pagination. Provide an object ID to fetch the previous page before that ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_BATCHESTool to list your organization’s batches. Use when you need to view all batches, check batch statuses, or find a specific batch by listing them.

Input Parameters

string
A cursor for use in pagination. Provide an object ID to fetch the next page of the list after that ID.
integer
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_CHAT_COMPLETIONSTool to list stored chat completions that were created with the store parameter set to true. Use to retrieve previously stored completions for review, analysis, or audit purposes.

Input Parameters

string
Cursor for pagination. Provide the ID of the last chat completion from the previous request to fetch the next page
integer
Number of chat completions to retrieve. Default is 20
string
Filter by the model used to generate the chat completions
string ("asc" | "desc")
Sort order for chat completions.
string
Filter by metadata keys. Format: metadata[key1]=value1&metadata[key2]=value2

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_CHATKIT_THREAD_ITEMSList items from a ChatKit thread, including messages, tool calls, and tasks. Results are paginated.

Input Parameters

string
List items created after this thread item ID. Defaults to null for the first page.
integer
Maximum number of thread items to return. Defaults to 20.
string ("asc" | "desc")
Order for listing thread items.
string
List items created before this thread item ID. Defaults to null for the newest results.
string
required
Identifier of the ChatKit thread whose items are requested.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_CONTAINER_FILESList files in a specific container. Results are paginated.

Input Parameters

string
Cursor for pagination. Provide an object ID to fetch the next page after that ID.
integer
Limit on the number of files to return (1-100). Default is 20.
string ("asc" | "desc")
Sort order for listing container files.
string
required
ID of the container to list files from

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_CONTAINERSList a page of containers, optionally filtering by name. Use the pagination cursor to retrieve further results.

Input Parameters

string
Filter results by container name.
string
A cursor for use in pagination. ‘after’ is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.
integer
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
string ("asc" | "desc")
Sort order for the created_at timestamp.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_CONVERSATION_ITEMSList a page of items in a conversation by ID for review or processing. Use the pagination cursor to retrieve further items.

Input Parameters

string
An item ID to list items after, used in pagination.
integer
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
string ("asc" | "desc")
Order for listing conversation items.
array
Specify additional output data to include in the model response. Currently supported values are: web_search_call.action.sources, code_interpreter_call.outputs, computer_call_output.output.image_url, file_search_call.results, message.input_image.image_url, message.output_text.logprobs, reasoning.encrypted_content.
string
required
The ID of the conversation to list items for.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_ENGINESTool to list available engines and their basic information. Use when you need to discover which engines are available.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_EVALSTool to list evaluations for a project. Use when you need to view all evaluations, check their configurations, or find a specific evaluation by listing them.

Input Parameters

string
Identifier for the last eval from the previous pagination request.
integer
Number of evals to retrieve. Defaults to 20.
string ("asc" | "desc")
Sort order for evals by timestamp.
string ("created_at" | "updated_at")
Field to order evals by.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_FILESLists files in the authenticated organization/project context. Results are cursor-paginated; use the returned last ID as the next request’s after cursor when more results are available.

Input Parameters

string
Cursor for pagination. Use the last_id from a previous response to fetch the next page of results.
integer
Number of files to retrieve
string ("asc" | "desc")
Sort order by created_at timestamp. ‘asc’ for ascending, ‘desc’ for descending. Defaults to ‘desc’.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_FILES_IN_VECTOR_STORE_BATCHTool to list vector store files in a batch. Use when you need to retrieve all files that were added to a vector store as part of a specific batch operation.

Input Parameters

string
A cursor for use in pagination. ‘after’ is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.
integer
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
string ("asc" | "desc")
Sort order for listing files.
string
A cursor for use in pagination. ‘before’ is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
string ("in_progress" | "completed" | "failed" | "cancelled")
Filter by file status.
string
required
The ID of the file batch that the files belong to.
string
required
The ID of the vector store that the files belong to.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_FINE_TUNESLists fine-tuning jobs for the authenticated context, with cursor pagination. An empty page does not necessarily mean that no jobs exist.

Input Parameters

string
Identifier for the last fine-tuning job from the previous pagination request.
integer
Number of fine-tuning jobs to retrieve (default 20).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_FINE_TUNING_EVENTSTool to get status updates for a fine-tuning job. Use when you need to monitor the progress of a fine-tuning job or retrieve event logs.

Input Parameters

string
Identifier for the last event from the previous pagination request.
integer
Number of events to retrieve.
string
required
The ID of the fine-tuning job to get events for.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_FINE_TUNING_JOB_CHECKPOINTSTool to list checkpoints for a fine-tuning job. Use when you need to retrieve model checkpoints created during the fine-tuning process. Checkpoints are created at various steps during training and can be used to evaluate model performance at different stages.

Input Parameters

string
Identifier for the last checkpoint ID from the previous pagination request.
integer
Number of checkpoints to retrieve.
string
required
The ID of the fine-tuning job to get checkpoints for.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_INPUT_ITEMSTool to retrieve input items for a given response from the OpenAI Responses API. Use when you need to inspect the inputs that were used to generate a specific response.

Input Parameters

string
An item ID to list items after, used in pagination
integer
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20
string ("asc" | "desc")
Sort order for listing input items.
array
Additional fields to include in the response
string
required
The ID of the response to retrieve input items for

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_MESSAGESList messages in an Assistants thread, including outputs generated by a run. Results can be filtered by run and paginated using cursors, with a page size of 1–100 and creation-time ordering. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
Cursor for pagination. Provide an object ID to fetch the next page after that ID.
integer
Limit on the number of messages to return (1-100). Default is 20.
string ("asc" | "desc")
Sort order by created_at timestamp: ‘asc’ for ascending, ‘desc’ for descending. Default is ‘desc’.
string
Cursor for pagination. Provide an object ID to fetch the previous page before that ID.
string
Filter messages by the run ID that generated them
string
required
The ID of the thread to retrieve messages from

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_MODELSLists models available to the current account or organization, with model identifiers and ownership metadata. Results may include deprecated or assistant-incompatible models.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_RUNSList a page of Assistants runs belonging to a thread to inspect their status or execution history. The legacy operation supports ordering and cursor pagination. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses and Conversations APIs.

Input Parameters

string
Cursor for pagination. Provide an object ID to fetch the next page after that ID.
integer
Limit on the number of runs to return (1-100). Default is 20.
string ("asc" | "desc")
Sort order by created_at timestamp: ‘asc’ for ascending, ‘desc’ for descending. Default is ‘desc’.
string
Cursor for pagination. Provide an object ID to fetch the previous page before that ID.
string
required
ID of the thread to list runs from

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_RUN_STEPSList steps in an Assistants API run to inspect execution progress, tool calls, and message creation events. Supports pagination, ordering, and optional file search result content. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
Cursor for pagination. Provide an object ID to fetch the next page after that ID.
integer
Limit on the number of run steps to return (1-100). Default is 20.
string ("asc" | "desc")
Sort order by created_at timestamp: ‘asc’ for ascending, ‘desc’ for descending. Default is ‘desc’.
string
Cursor for pagination. Provide an object ID to fetch the previous page before that ID.
string
required
The ID of the run to list steps from
array
Additional fields to include in the response. Use ‘step_details.tool_calls[].file_search.results[].content’ to include file search result content.
string
required
The ID of the thread that was run

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_SKILLSList skills with pagination and timestamp ordering, returning their IDs, names, and descriptions.

Input Parameters

string
Identifier for the last item from the previous pagination request
integer
Number of skills to retrieve
string ("asc" | "desc")
Sort order for listing skills.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_THREADSTool to list ChatKit threads with pagination and filtering. Use when you need to retrieve threads for a specific user or browse all available threads.

Input Parameters

string
Filter threads that belong to this user identifier. Defaults to null to return all users.
string
List items created after this thread item ID. Defaults to null for the first page.
integer
Maximum number of thread items to return. Defaults to 20.
string ("asc" | "desc")
Sort order for results by creation time. Defaults to ‘desc’.
string
List items created before this thread item ID. Defaults to null for the newest results.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_VECTOR_STORE_FILESTool to list files in a vector store. Use when you need to retrieve all files attached to a specific vector store.

Input Parameters

string
A cursor for use in pagination. ‘after’ is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.
integer
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
string ("asc" | "desc")
Sort order for listing files.
string
A cursor for use in pagination. ‘before’ is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
string ("in_progress" | "completed" | "failed" | "cancelled")
Filter by file status.
string
required
The ID of the vector store that the files belong to.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_VECTOR_STORESTool to list vector stores to discover available vector stores by name or metadata. Use when you need to view all vector stores in your organization.

Input Parameters

string
Cursor for pagination. Provide an object ID to fetch the next page after that ID.
integer
Limit on the number of vector stores to return (1-100). Default is 20.
string ("asc" | "desc")
Sort order by created_at timestamp: ‘asc’ for ascending, ‘desc’ for descending. Default is ‘desc’.
string
Cursor for pagination. Provide an object ID to fetch the previous page before that ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_LIST_VIDEOSList video generation jobs and their statuses, with pagination and timestamp ordering, to review multiple tasks. DEPRECATED: OpenAI’s Videos API was shut down on September 24, 2026.

Input Parameters

string
Cursor for pagination. Provide a video ID to fetch the next page after that ID.
integer
Number of videos to retrieve
string ("asc" | "desc")
Sort order options for listing videos.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_MODIFY_ASSISTANTModify an existing Assistants API assistant’s configuration, such as its model, instructions, tools, or metadata. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
The name of the assistant. The maximum length is 256 characters.
string
ID of the model to use. You can use the List models API to see all available models.
array
A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, file_search, or function.
number
An alternative to sampling with temperature, 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.
object
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.
string
The description of the assistant. The maximum length is 512 characters.
number
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
string
required
The ID of the assistant to modify
string
The system instructions that the assistant uses. The maximum length is 256,000 characters.
object
Tool resources for the assistant.
string
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106. Setting to { ‘type’: ‘json_object’ } enables JSON mode.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_MODIFY_MESSAGEModify metadata on a specific message in an Assistants conversation thread, identified by thread and message IDs. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

object
Set of up to 16 key-value pairs that can be attached to the message. Keys can be max 64 characters and values max 512 characters.
string
required
The ID of the thread to which this message belongs
string
required
The ID of the message to modify

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_MODIFY_RUNUpdate metadata on a specific Assistants run identified by its thread and run IDs. DEPRECATED: The Assistants API was shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
required
The ID of the run to modify
object
Set of up to 16 key-value pairs that can be attached to the run. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. This can be useful for storing additional information about the run in a structured format
string
required
The ID of the thread that was run

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_MODIFY_THREADUpdate metadata on an existing Assistants API thread identified by its thread ID. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

object
Arbitrary JSON metadata to attach to the thread Values must be short strings; large, nested, or complex payloads are rejected.
string
required
ID of the thread to modify

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_MODIFY_VECTOR_STORETool to modify an existing vector store. Use when you need to update the name, expiration policy, or metadata of a vector store.

Input Parameters

string
The name of the vector store.
object
Set of up to 16 key-value pairs that can be attached to the vector store. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. Pass null to clear existing metadata.
object
Expiration policy for a vector store.
string
required
The ID of the vector store to modify.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_ASSISTANTRetrieve a specific assistant by ID to inspect its configuration and metadata. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses and Conversations APIs.

Input Parameters

string
required
Identifier of the assistant to retrieve (path parameter) Must be a valid, stored OpenAI assistant ID; stale or incorrect IDs cause failed retrievals and require additional lookup calls.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_BATCHTool to retrieve a batch by ID to check its status, progress, and results. Use when you need to check the current state of a batch job, view completion statistics, or access output file IDs.

Input Parameters

string
required
The ID of the batch to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_CONTAINERTool to retrieve details of a specific container by its ID. Use when you need to fetch container configuration, status, or metadata.

Input Parameters

string
required
Identifier of the container to retrieve (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_CONTAINER_FILETool to retrieve metadata for a specific file in a container. Use when you need to get details about a container file including its size, path, and creation timestamp.

Input Parameters

string
required
ID of the file to retrieve from the container
string
required
ID of the container containing the file

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_CONTAINER_FILE_CONTENTTool to retrieve the content of a file within a container. Use when you need to download or access the actual file data from a container.

Input Parameters

string
required
Identifier of the file within the container (path parameter)
string
required
Identifier of the container (path parameter)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_ENGINERetrieve a legacy OpenAI engine by ID to inspect its availability and metadata. DEPRECATED: The engines endpoint was shut down in 2022; use the models endpoint instead.

Input Parameters

string
required
Identifier of the engine to retrieve (e.g., gpt-4o-mini, gpt-4, dall-e-3)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_FILETool to retrieve information about a specific file. Use when you need to check the details, status, or metadata of a file by its ID.

Input Parameters

string
required
The ID of the file to use for this request.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_FINE_TUNING_JOBTool to retrieve information about a fine-tuning job. Use when you need to check the status, progress, or details of an existing fine-tuning job.

Input Parameters

string
required
The ID of the fine-tuning job to retrieve

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_MODELTool 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. Use before depending on a model ID in downstream calls.

Input Parameters

string
required
Identifier of the model to retrieve (path parameter) Case-sensitive; use exact IDs as returned by OPENAI_LIST_MODELS.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_RUNRetrieve an Assistants run by thread and run ID to check its status, errors, and usage, such as when polling for completion before reading thread messages. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses and Conversations APIs.

Input Parameters

string
required
ID of the run to retrieve
string
required
ID of the thread that was run

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_THREADRetrieve an Assistants API thread by ID to inspect its metadata; message bodies are obtained separately. DEPRECATED: The Assistants API shut down on August 26, 2026. Migrate to the Responses API and Conversations API.

Input Parameters

string
required
Identifier of the thread to retrieve (path parameter) Must be captured from OPENAI_CREATE_THREAD and persisted — no API exists to list or discover existing thread IDs. Reuse consistently across OPENAI_CREATE_MESSAGE calls; mismatched IDs send operations to the wrong context.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RETRIEVE_VECTOR_STORE_FILE_CONTENTTool to retrieve the parsed contents of a vector store file. Use when you need to access the actual text content that has been processed and chunked for a file in a vector store.

Input Parameters

string
required
The ID of the file within the vector store to retrieve content from.
string
required
The ID of the vector store that the file belongs to.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_RUN_GRADERTool to run a grader to evaluate model performance on a given sample. Use when you need to evaluate model outputs against expected results using various grading strategies like string matching, text similarity, custom Python code, or model-based scoring.

Input Parameters

object
The dataset item provided to the grader. This will be used to populate the ‘item’ namespace. See the guide for more details
string
required
The grader configuration to use for evaluation. Can be one of: StringCheckGrader (compares strings), TextSimilarityGrader (evaluates text similarity), PythonGrader (runs custom Python code), ScoreModelGrader (uses a model for scoring), or MultiGrader (combines multiple graders)
string
required
The model sample output to be evaluated. This value will be used to populate the ‘sample’ namespace. The ‘output_json’ variable will be populated if the model sample is a valid JSON string

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_SEARCH_VECTOR_STORETool to search a vector store for relevant chunks based on a query and file attributes filter. Use when you need to find specific content within a vector store for retrieval-augmented generation (RAG) or custom search workflows.

Input Parameters

string
required
A query string or array of strings for the search.
object
A filter to apply based on file attributes. Can be a comparison filter with ‘type’, ‘key’, and ‘value’ fields, or a compound filter with ‘type’ and ‘filters’ fields combining multiple filters.
boolean
Whether to rewrite the natural language query for vector search.
integer
The maximum number of results to return. Must be between 1 and 50.
object
Ranking options for search.
string
required
The ID of the vector store to search.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_SUBMIT_TOOL_OUTPUTS_TO_RUNSubmit all tool call outputs together to continue an Assistants API run whose required action is submit_tool_outputs. DEPRECATED: The Assistants API shut down on August 26, 2026; migrate to the Responses API and Conversations API.

Input Parameters

string
required
The ID of the run that requires the tool output submission. The run must have status ‘requires_action’ and required_action.type must be ‘submit_tool_outputs’
boolean
If true, returns a stream of events during the run execution after submitting tool outputs
string
required
The ID of the thread to which this run belongs
array
required
A list of tools for which the outputs are being submitted. All tool outputs must be submitted in a single request

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_UPDATE_CHAT_COMPLETIONTool to update metadata for a stored chat completion. Use when you need to modify tags or metadata for a completion that was created with store=true.

Input Parameters

object
Developer-defined tags and values to update for the chat completion. Pass null to clear metadata. All values must be strings
string
required
The ID of the chat completion to update. Only completions created with store=true can be modified

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_UPDATE_CONVERSATIONTool to update a conversation’s metadata. Use when you need to modify metadata for an existing conversation.

Input Parameters

object
Optional metadata key-value pairs to attach to the conversation. Up to 16 pairs allowed, with keys ≤64 chars and values ≤512 chars. Pass null to clear metadata.
string
required
The ID of the conversation to update.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_UPDATE_EVALUpdates an evaluation’s name or metadata without changing its data source configuration or testing criteria. OpenAI has scheduled existing evals to become read-only on October 31, 2026, and the Evals API to shut down on November 30, 2026.

Input Parameters

string
New name for the evaluation
string
required
The ID of the evaluation to update
object
New metadata to attach to the evaluation. This replaces any existing metadata

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_UPDATE_VECTOR_STORE_FILE_ATTRIBUTESTool to update custom attributes on a vector store file. Use when you need to add or modify metadata associated with files in a vector store.

Input Parameters

string
required
The ID of the file to update attributes.
object
Custom attributes to associate with the file. Can be any JSON object with key-value pairs, or null to clear attributes.
string
required
The ID of the vector store the file belongs to.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_UPLOAD_FILEUpload file bytes to OpenAI for a specified purpose, such as fine-tuning, and return the uploaded file’s details. The file ID can be used to reference the upload in subsequent operations.

Input Parameters

string
required
Binary content of the file to upload. E.g., open(‘data.jsonl’,‘rb’).read().
string
required
Intended purpose of the uploaded file. Currently only ‘fine-tune’ is supported.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: OPENAI_VALIDATE_GRADERTool to validate a grader configuration for fine-tuning jobs. Use when you need to verify that a grader is correctly configured before using it in a fine-tuning job.

Input Parameters

string
required
The grader configuration to validate. Can be one of: StringCheckGrader (for string comparisons), TextSimilarityGrader (for semantic similarity), PythonGrader (for custom Python logic), ScoreModelGrader (for model-based scoring), or MultiGrader (for combining multiple graders)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not