Description

Build next-gen apps with OpenAI’s powerful models.

The OpenAI API can be applied to virtually any task that involves understanding or generating natural language or code. It offers a spectrum of models with different levels of power suitable for different tasks, as well as the ability to fine-tune your own custom models. These models can be used for everything from content generation to semantic search and classification:

  • GPT-3, GPT-3.5 and GPT-4: Perform a variety of natural language tasks.
  • Codex: Translates natural language to code.
  • DALL-E: Creates and edits original images.
  • Whisper: A general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.

Lightning Fast

The OpenAI APIs advanced inference infrastructure provides extremely short response times.

Scalable

It can handle high volume requests that scale with your needs.

Flexible

Easy to use and flexible enough to make machine learning teams more productive.

Supported Operations

OpenAI API

Returns a list of assistants.

Endpoint to retrieve a list of assistants.

Create an assistant with a model and instructions.

Endpoint to create a new assistant with specified settings and configurations.

Retrieves an assistant.

Retrieves details of a specific assistant identified by its unique ID.

Modifies an assistant.

Modifies an existing assistant with specified settings and configurations.

Delete an assistant.

Deletes the specified assistant identified by its unique ID.

Generates audio from the input text.

This endpoint generates audio files from the provided input text using the specified model and voice.

Transcribes audio into the input language.

Converts audio files into written text using the selected model.

Translates audio into English.

Translates audio content, such as speech in different languages, into written English text using the specified model. Ideal for transcribing and understanding spoken foreign language content.

List your organization's batches.

List your organization's batches.

Creates and executes a batch from an uploaded file of requests

Creates and executes a batch from an uploaded file of requests

Retrieves a batch.

Retrieves a batch.

Cancels an in-progress batch. The batch will be in status `cancelling` for up to 10 minutes, before changing to `cancelled`, where it will have partial results (if any) available in the output file.

Cancels an in-progress batch. The batch will be in status `cancelling` for up to 10 minutes, before changing to `cancelled`, where it will have partial results (if any) available in the output file.

Creates a model response for the given chat conversation.

Creates model responses for chat conversations by providing a sequence of messages as input. This functionality returns a chat completion object with information about the model's response, message content, and completion tokens utilized. This allows you to engage in dynamic conversations with OpenAI models, including incorporating function calls when needed.

Creates a completion for the provided prompt and parameters.

Generates text completions based on a given prompt and configurable parameters.

Creates an embedding vector representing the input text.

Creates an embedding vector that represents the input text. This endpoint allows you to obtain a numeric representation of a given text using the specified language model. You can specify the model to use, the input text for which you want an embedding, and the encoding format, which can be float or string. The response provides a list of embeddings, with each embedding containing a set of numeric values. These embeddings can be used for various natural language processing tasks, such as similarity analysis, clustering, and classification, and offer a way to convert text data into a format that machine learning algorithms can work with.

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

Retrieves a list of files associated with the user's organization. These files can be used for various purposes, such as data storage and reference. The response includes information about each file, including its ID, size in bytes, creation timestamp, filename, and purpose.

Upload a file that can be used across various endpoints. Individual files can be up to 512 MB, and the size of all files uploaded by one organization can be up to 100 GB. The Assistants API supports files up to 2 million tokens and of specific file types. See the [Assistants Tools guide](/docs/assistants/tools) for details. The Fine-tuning API only supports `.jsonl` files. The input also has certain required formats for fine-tuning [chat](/docs/api-reference/fine-tuning/chat-input) or [completions](/docs/api-reference/fine-tuning/completions-input) models. The Batch API only supports `.jsonl` files up to 100 MB in size. The input also has a specific required [format](/docs/api-reference/batch/request-input). Please [contact us](https://help.openai.com/) if you need to increase these storage limits.

Upload a file that can be used across various endpoints. The size of all the files uploaded by one organization can be up to 100 GB. The size of individual files can be a maximum of 512 MB or 2 million tokens for Assistants. See the [Assistants Tools guide](/docs/assistants/tools) to learn more about the types of files supported. The Fine-tuning API only supports `.jsonl` files. Please [contact us](https://help.openai.com/) if you need to increase these storage limits.

Returns information about a specific file.

Retrieves information about a specific file within the organization. You must provide the ID of the file you want to retrieve. The response includes details about the file, such as its ID, size in bytes, creation timestamp, filename, and purpose.

Delete a file.

Deletes a specific file associated with the organization. To execute this operation, you need to provide the ID of the file to be deleted. The response indicates whether the file was successfully deleted.

Returns the contents of the specified file.

Retrieves and returns the content of the specified file within the organization. To access the content, provide the ID of the file in the request. The response contains the content of the file, which can be downloaded and saved for further use.

List your organization's fine-tuning jobs

Lists fine-tuning jobs associated with your organization in a paginated format. You can specify the after parameter to retrieve jobs starting from a specific identifier and control the number of jobs to retrieve with the limit parameter. The response includes a list of fine-tuning job objects and whether more jobs are available for pagination.

Creates a fine-tuning job which begins the process of creating a new 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. [Learn more about fine-tuning](/docs/guides/fine-tuning)

Creates a fine-tuning job that refines a specified model using a provided dataset. The response contains information about the enqueued job, including its status and the name of the fine-tuned model once the process is complete. For more details on fine-tuning, please refer to the [fine-tuning guide](/docs/guides/fine-tuning).

Get info about a fine-tuning job. [Learn more about fine-tuning](/docs/guides/fine-tuning)

Retrieves detailed information about a specific fine-tuning job using its unique ID. The response includes data related to the fine-tuning process, such as the model used, timestamps, the fine-tuned model name, organization ID, result files, job status, training file, hyperparameters, and the number of trained tokens. For a deeper understanding of fine-tuning, please refer to the [fine-tuning guide](/docs/guides/fine-tuning).

Immediately cancel a fine-tune job.

Allows immediate cancellation of a specific fine-tuning job using its unique ID. When a job is canceled, it will stop the fine-tuning process. The response includes information about the canceled fine-tuning job, including its status, model, creation timestamp, organization ID, result files, hyperparameters, and related files.

List checkpoints for a fine-tuning job.

List checkpoints for a fine-tuning job.

Get status updates for a fine-tuning job.

Retrieves status updates and events related to a specific fine-tuning job using its unique ID. Users can specify the after parameter to start from a particular event and control the number of events to retrieve with the limit parameter. The response includes a list of fine-tuning event objects, providing information on the events that occurred during the fine-tuning process.

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

Creates an edited or extended image by combining an original image with a user-provided prompt. This endpoint allows you to take an existing image, apply modifications or extensions specified in the prompt, and generate a new image based on the combination. The edited image is created by considering both the visual content of the original image and the textual input from the prompt, resulting in a creative and context-aware image transformation. This API call takes the original image, a prompt, and optional parameters to control the image generation process, producing a list of edited images.

Creates an image given a prompt.

Creates an image based on a provided prompt.

Creates a variation of a given image.

Creates a variation of a given image by applying artistic modifications, styles, and transformations. This API call takes an original image as a base and generates multiple artistic variations of that image. These variations are produced based on the provided image, and you can specify the number of variations to generate, as well as the desired size of the output images. This endpoint offers a creative way to explore artistic interpretations of your images, providing a list of edited image variations that can add a unique touch to your visual content.

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

List the currently available models and provide basic information about each model, including the owner and availability. You can use this endpoint to discover the models you can use for various tasks.

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

Retrieve detailed information about a specific model, including details such as the model owner and permissions. You can use this endpoint to gather information about a specific model based on its unique ID.

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

Delete a fine-tuned model. To delete a model, you must have the Owner role in your organization. This operation allows you to remove a model from your available models.

Classifies if text is potentially harmful.

This endpoint is used to classify whether a given text violates OpenAI's Content Policy. You can submit text for moderation, and it will return a moderation object that provides information about whether the text contains content that goes against OpenAI's guidelines. The response includes details such as whether the text is flagged and the categories it might fall under, such as sexual content, hate speech, harassment, self-harm, and more.

Create a thread.

Creates a new thread, typically initiated by a user, in the conversational context.

Create a thread and run it in one request.

Create a thread and run it in a single request.

Retrieves a thread.

Retrieves a specific thread by its unique identifier.

Modifies a thread.

Modifies a specific thread by updating its metadata.

Delete a thread.

Deletes a specific thread.

Returns a list of messages for a given thread.

Retrieves a list of messages for a given thread.

Create a message.

Creates a message for a given thread.

Retrieve a message.

Retrieves a message belonging to a specific thread.

Modifies a message.

Modifies a message belonging to a specific thread.

Deletes a message.

Deletes a message.

Returns a list of runs belonging to a thread.

Returns a list of runs belonging to a thread.

Create a run.

This endpoint creates a new run for a specified thread, facilitating the execution of an assistant's responses within the thread.

Retrieves a run.

This endpoint retrieves information about a specific run within a thread, including its status, timestamps, associated files, and metadata.

Modifies a run.

This endpoint modifies a specific run within a thread, allowing updates to its metadata.

Cancels a run that is `in_progress`.

Cancels a run that is currently in progress within the specified thread.

Returns a list of run steps belonging to a run.

Returns a list of steps associated with a specific run within a thread.

Retrieves a run step.

Retrieves information about a specific run step within a thread, including its type, status, timestamps, and usage statistics.

When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request.

When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request.

Returns a list of vector stores.

Returns a list of vector stores.

Create a vector store.

Create a vector store.

Retrieves a vector store.

Retrieves a vector store.

Modifies a vector store.

Modifies a vector store.

Delete a vector store.

Delete a vector store.

Create a vector store file batch.

Create a vector store file batch.

Retrieves a vector store file batch.

Retrieves a vector store file batch.

Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.

Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.

Returns a list of vector store files in a batch.

Returns a list of vector store files in a batch.

Returns a list of vector store files.

Returns a list of vector store files.

Create a vector store file by attaching a [File](/docs/api-reference/files) to a [vector store](/docs/api-reference/vector-stores/object).

Create a vector store file by attaching a [File](/docs/api-reference/files) to a [vector store](/docs/api-reference/vector-stores/object).

Retrieves a vector store file.

Retrieves a vector store file.

Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the [delete file](/docs/api-reference/files/delete) endpoint.

Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the [delete file](/docs/api-reference/files/delete) endpoint.

Details
Last Update

2 weeks ago

Includes
openai-api-client
openai-auth