{"@context": "https://schema.org", "@type": "WebAPI", "name": "OpenAI API API", "description": "APIs for sampling from and fine-tuning language models", "provider": {"@type": "Organization", "name": "openai.com"}, "documentation": "https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml"}
Index / APIs / openai.com

OpenAI API API

APIs for sampling from and fine-tuning language models

Every row below was read from the vendor's own OpenAPI document. The summary text is theirs. What this registry adds is that each operation is indexed with its method, path, base URL and auth scheme, so a search for a capability can answer with a call rather than a name, and that the endpoint is probed on a schedule.

Specifications as held by the APIs.guru corpus, whose newest record is 2023-04-21. Operations the vendor has added since are not listed here; the origin links above are the vendor's own current documents.

base URLs: https://api.openai.com/v1

find it by capability: POST /search {"query":{"text":"..."}} returns these operations with their invocation detail. Connect any agent client.

OpenAI API v1.2.0

APIs for sampling from and fine-tuning language models

methodpathwhat the vendor says it does
POST/answersAnswers the specified question using the provided documents and examples. The endpoint first [searches](/docs
POST/audio/transcriptionsTranscribes audio into the input language. OpenAI
POST/audio/translationsTranslates audio into into English. OpenAI
POST/chat/completionsCreates a completion for the chat message OpenAI
POST/classificationsClassifies the specified `query` using provided examples. The endpoint first [searches](/docs/api-reference/s
POST/completionsCreates a completion for the provided prompt and parameters OpenAI
POST/editsCreates a new edit for the provided input, instruction, and parameters. OpenAI
POST/embeddingsCreates an embedding vector representing the input text. OpenAI
GET/enginesLists the currently available (non-finetuned) models, and provides basic information about each one such as th
GET/engines/{engine_id}Retrieves a model instance, providing basic information about it such as the owner and availability. OpenAI
POST/engines/{engine_id}/searchThe search endpoint computes similarity scores between provided query and documents. Documents can be passed d
GET/filesReturns a list of files that belong to the user's organization. OpenAI
POST/filesUpload a file that contains document(s) to be used across various endpoints/features. Currently, the size of a
GET/files/{file_id}Returns information about a specific file. OpenAI
DELETE/files/{file_id}Delete a file. OpenAI
GET/files/{file_id}/contentReturns the contents of the specified file OpenAI
GET/fine-tunesList your organization's fine-tuning jobs OpenAI
POST/fine-tunesCreates a job that fine-tunes a specified model from a given dataset. Response includes details of the enqueu
GET/fine-tunes/{fine_tune_id}Gets info about the fine-tune job. [Learn more about Fine-tuning](/docs/guides/fine-tuning) OpenAI
POST/fine-tunes/{fine_tune_id}/cancelImmediately cancel a fine-tune job. OpenAI
GET/fine-tunes/{fine_tune_id}/eventsGet fine-grained status updates for a fine-tune job. OpenAI
POST/images/editsCreates an edited or extended image given an original image and a prompt. OpenAI
POST/images/generationsCreates an image given a prompt. OpenAI
POST/images/variationsCreates a variation of a given image. OpenAI
GET/modelsLists the currently available models, and provides basic information about each one such as the owner and avai
GET/models/{model}Retrieves a model instance, providing basic information about the model such as the owner and permissioning. O
DELETE/models/{model}Delete a fine-tuned model. You must have the Owner role in your organization. OpenAI
POST/moderationsClassifies if text violates OpenAI's Content Policy OpenAI

specification origin: https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml

nothing on this page is a rating, an endorsement or a claim about quality. Reachability is what our probes observed from one network; answering is a floor under usefulness, not a measure of it.