Create an assistant with a model and instructions

The description of the assistant The maximum length is 512 characters

The system instructions that the assistant uses

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

What sampling temperature to use, between 0 and 2

A set of resources that are used by the assistant's tools

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass

A limit on the number of objects to be returned

limit

Sort order by the created_at timestamp of the objects

order

after

before

assistant_id

A list of File IDs attached to this assistant

 Specifies the format that the model must output

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

Transcribes audio into the input language

The audio file to transcribe in one of these formats

file

ID of the model to use. Only whisper-1 is currently available

model

The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency

language

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language

prompt

The format of the transcript output; in one of these options

response_format

The sampling temperature; between 0 and 1. Higher values like 0.8 will make the output more random; while lower values like 0.2 will 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

temperature

The timestamp granularities to populate for this transcription

timestamp_granularities[]

The format to audio in. Supported formats are mp3 opus aac and flac

The voice to use when generating the audio

Creates a completion for the chat message.


List of available models for ChatGPT API:  


`gpt-3.5-turbo` (Current)

`gpt-3.5-turbo-16k`

`gpt-3.5-turbo-instruct`


`gpt-4` 

`gpt-4-32k`

`gpt-4-1106-preview`

`gpt-4-vision-preview`


[Official OpenAI model here: https://platform.openai.com/docs/models](https://platform.openai.com/docs/models)

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

Modify the likelihood of specified tokens appearing in the completion

Whether to return log probabilities of the output tokens or not

The maximum number of tokens allowed for the generated answer. By default the number of tokens the model can return will be (4096 - prompt tokens)

The messages to generate chat completions for; in the chat format

ID of the model to use. Currently only gpt-3.5-turbo and gpt-3.5-turbo-0301 are supported

How many chat completion choices to generate for each input message

Whether to enable parallel function calling during tool use

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

An object specifying the format that the model must output

Up to 4 sequences where the API will stop generating further tokens

If set; partial message deltas will be sent like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available; with the stream terminated by a data - [DONE] message

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

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message

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

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

A unique identifier representing your end-user which can help OpenAI to monitor and detect abuse

Creates an embedding vector representing the input text

The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models

The format to return the embeddings in. Can be either float or base64.

Input text to embed, encoded as a string or array of tokens

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

Return a list of files that belong to the user's organization

purpose

Upload a file that contains document(s) to be used across various endpoints/features. Currently, the size of all the files uploaded by one organization can be up to 1 GB. Please contact us if you need to increase the storage limit

The File object (not file name) to be uploaded

The intended purpose of the uploaded file

The ID of the file to use for this request

file_id

Returns information about a specific file

Returns the contents of the specified file

Creates a job that fine-tunes a specified model from a given dataset. Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete

The ID of an uploaded file that contains training data

training_file

The hyperparameters used for the fine-tuning job

hyperparameters

A string of up to 18 characters that will be added to your fine-tuned model name

suffix

The ID of an uploaded file that contains validation data

validation_file

A list of integrations to enable for your fine-tuning job

integrations

The weight to use for loss on the prompt tokens

seed

List your organization's fine-tuning jobs

Identifier for the last job from the previous pagination request

The ID of the fine-tuning job to get events for

fine_tuning_job_id

Identifier for the last event from the previous pagination request

Get fine-grained status updates for a fine-tune job

Specify the number of images to generate, between 1 and 10; for DALL-E 3, only n=1 is supported.

Provide a text description of the desired image(s), with a maximum length of 1000 characters for DALL-E 2 and 4000 characters for DALL-E 3.

Specify the quality of the image; 'hd' creates images with finer details and greater consistency, supported only for DALL-E 3.

Specify the format of the generated images, either 'url' or 'b64_json'; URLs are valid for 60 minutes after generation.

Specify the size of the generated images: 256x256, 512x512, or 1024x1024 for DALL-E 2; 1024x1024, 1792x1024, or 1024x1792 for DALL-E 3.

Provide a unique identifier representing your end-user to help OpenAI monitor and detect abuse.

Creates an edited or extended image given an original image and a prompt

Provide the image to edit, which must be a valid PNG file, less than 4MB, and square; if no mask is provided, the image must have transparency to be used as the mask

image

Provide a text description of the desired image(s) within a maximum length of 1000 characters

Provide an additional image where fully transparent areas (alpha zero) indicate where edits should be applied, valid as a PNG file, less than 4MB, and matching the dimensions of the main image

mask

Specify the model for image generation; only DALL-E 2 is supported at this time

The number of images to generate. Must be between 1 and 10

The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024

size

Specify the format for the generated images: 'url' or 'b64_json'. URLs are valid for 60 minutes after generation

user

The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square

The model to use for image generation. Only dall-e-2 is supported at this time

The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported

The format in which the generated images are returned. Must be one of url or b64_json. URLs are only valid for 60 minutes after the image has been generated

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse

thread_id

A list of files attached to the message, and the tools they should be added to

The role of the entity that is creating the message

Returns a list of messages for a given thread

The ID of the thread the messages belong to

Filter messages by the run ID that generated them

run_id

The ID of the thread to which this message belongs

message_id

Lists the currently available models, and provides basic information about each one such as the owner and availability

Delete a fine-tuned model. You must have the Owner role in your organization

Retrieves a model instance, providing basic information about the model such as the owner and permissioning

The ID of the model to use for this request

Classifies if text violates OpenAI's Content Policy

Two content moderations models are available: text-moderation-stable and text-moderation-latest

The ID of the thread to which the run and run step belongs

The ID of the run to which the run step belongs

step_id

Returns a list of run steps belonging to a run

The ID of the thread the run and run steps belong to

The ID of the run the run steps belong to

Set of 16 key-value pairs that can be attached to an object

The ID of the assistant to use to execute this run

Override the default system message of the assistant

The maximum number of completion tokens that may be used over the course of the run

The maximum number of prompt tokens that may be used over the course of the run

The ID of the Model to be used to execute this run

Specifies the format that the model must output

If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message

Controls which (if any) tool is called by the model

Override the tools the assistant can use for this run

Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run

Returns a list of runs belonging to a thread

A limit on the number of objects to be returned. Defaults:20

All outputs must be submitted in a single request

The ID of the thread to which this run belongs

The ID of the run that requires the tool output submission

A list of tools for which the outputs are being submitted

Create a thread and run it in one request

A list of messages to start the thread with

A set of resources that are made available to the assistant's tools in this thread

The ID of the thread to modify. Only the metadata can be modified

OpenAI

Pre-configured, Predictable, Single Interface, Ready-to-use, Opinionated & Managed API Explorer & Server - LowCodeAPI

Pre-configured, Predictable, Single Interface, Ready-to-use, Opinionated & Managed API Explorer & Server. Bring your API credentials, configure and access your 3rd party APIs. Using LowCodeAPI securely manage all integrations in one place.

LowCodeAPI

Featured

Google Sheets

Google Docs

Notion

Gmail

gmail

Unsplash

UnsplashAPI

Cal API

Trello

Trello API

Telegram

Telegram API

The Stripe API is organized around REST. Our API has predictable resource-oriented URLs, accepts form-encoded request bodies, returns JSON-encoded responses, and uses standard HTTP response codes, authentication, and verbs.