OpenAI Completions API

openapi: 3.0.0
info:
  title: OpenAI Assistants Completions API
  description: The Assistants API allows you to build AI assistants within your own applications. An Assistant has instructions and can leverage models, tools, and knowledge to respond to user queries. The Assistants API currently supports three types of tools - Code Interpreter, Retrieval, and Function calling. In the future, we plan to release more OpenAI-built tools, and allow you to provide your own tools on our platform.
  version: 2.0.0
  termsOfService: https://openai.com/policies/terms-of-use
  contact:
    name: OpenAI Support
    url: https://help.openai.com/
  license:
    name: MIT
    url: https://github.com/openai/openai-openapi/blob/master/LICENSE
servers:
- url: https://api.openai.com/v1
security:
- ApiKeyAuth: []
tags:
- name: Completions
  description: Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.
paths:
  /completions:
    post:
      operationId: createCompletion
      tags:
      - Completions
      summary: OpenAI Creates a completion for the provided prompt and parameters.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateCompletionRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateCompletionResponse'
      x-oaiMeta:
        name: Create completion
        group: completions
        returns: 'Returns a [completion](/docs/api-reference/completions/object) object, or a sequence of completion objects if the request is streamed.

          '
        legacy: true
        examples:
        - title: No streaming
          request:
            curl: "curl https://api.openai.com/v1/completions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"VAR_model_id\",\n    \"prompt\": \"Say this is a test\",\n    \"max_tokens\": 7,\n    \"temperature\": 0\n  }'\n"
            python: "from openai import OpenAI\nclient = OpenAI()\n\nclient.completions.create(\n  model=\"VAR_model_id\",\n  prompt=\"Say this is a test\",\n  max_tokens=7,\n  temperature=0\n)\n"
            node.js: "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const completion = await openai.completions.create({\n    model: \"VAR_model_id\",\n    prompt: \"Say this is a test.\",\n    max_tokens: 7,\n    temperature: 0,\n  });\n\n  console.log(completion);\n}\nmain();"
          response: "{\n  \"id\": \"cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7\",\n  \"object\": \"text_completion\",\n  \"created\": 1589478378,\n  \"model\": \"VAR_model_id\",\n  \"system_fingerprint\": \"fp_44709d6fcb\",\n  \"choices\": [\n    {\n      \"text\": \"\\n\\nThis is indeed a test\",\n      \"index\": 0,\n      \"logprobs\": null,\n      \"finish_reason\": \"length\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 5,\n    \"completion_tokens\": 7,\n    \"total_tokens\": 12\n  }\n}\n"
        - title: Streaming
          request:
            curl: "curl https://api.openai.com/v1/completions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"VAR_model_id\",\n    \"prompt\": \"Say this is a test\",\n    \"max_tokens\": 7,\n    \"temperature\": 0,\n    \"stream\": true\n  }'\n"
            python: "from openai import OpenAI\nclient = OpenAI()\n\nfor chunk in client.completions.create(\n  model=\"VAR_model_id\",\n  prompt=\"Say this is a test\",\n  max_tokens=7,\n  temperature=0,\n  stream=True\n):\n  print(chunk.choices[0].text)\n"
            node.js: "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const stream = await openai.completions.create({\n    model: \"VAR_model_id\",\n    prompt: \"Say this is a test.\",\n    stream: true,\n  });\n\n  for await (const chunk of stream) {\n    console.log(chunk.choices[0].text)\n  }\n}\nmain();"
          response: "{\n  \"id\": \"cmpl-7iA7iJjj8V2zOkCGvWF2hAkDWBQZe\",\n  \"object\": \"text_completion\",\n  \"created\": 1690759702,\n  \"choices\": [\n    {\n      \"text\": \"This\",\n      \"index\": 0,\n      \"logprobs\": null,\n      \"finish_reason\": null\n    }\n  ],\n  \"model\": \"gpt-3.5-turbo-instruct\"\n  \"system_fingerprint\": \"fp_44709d6fcb\",\n}\n"
components:
  schemas:
    StopConfiguration:
      description: 'Not supported with latest reasoning models `o3` and `o4-mini`.


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

        returned text will not contain the stop sequence.

        '
      default: null
      nullable: true
      oneOf:
      - type: string
        default: <|endoftext|>
        example: '

          '
        nullable: true
      - type: array
        minItems: 1
        maxItems: 4
        items:
          type: string
          example: '["\n"]'
    CompletionUsage:
      type: object
      description: Usage statistics for the completion request.
      properties:
        completion_tokens:
          type: integer
          default: 0
          description: Number of tokens in the generated completion.
        prompt_tokens:
          type: integer
          default: 0
          description: Number of tokens in the prompt.
        total_tokens:
          type: integer
          default: 0
          description: Total number of tokens used in the request (prompt + completion).
        completion_tokens_details:
          type: object
          description: Breakdown of tokens used in a completion.
          properties:
            accepted_prediction_tokens:
              type: integer
              default: 0
              description: 'When using Predicted Outputs, the number of tokens in the

                prediction that appeared in the completion.

                '
            audio_tokens:
              type: integer
              default: 0
              description: Audio input tokens generated by the model.
            reasoning_tokens:
              type: integer
              default: 0
              description: Tokens generated by the model for reasoning.
            rejected_prediction_tokens:
              type: integer
              default: 0
              description: 'When using Predicted Outputs, the number of tokens in the

                prediction that did not appear in the completion. However, like

                reasoning tokens, these tokens are still counted in the total

                completion tokens for purposes of billing, output, and context window

                limits.

                '
        prompt_tokens_details:
          type: object
          description: Breakdown of tokens used in the prompt.
          properties:
            audio_tokens:
              type: integer
              default: 0
              description: Audio input tokens present in the prompt.
            cached_tokens:
              type: integer
              default: 0
              description: Cached tokens present in the prompt.
      required:
      - prompt_tokens
      - completion_tokens
      - total_tokens
    CreateCompletionResponse:
      type: object
      description: 'Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint).

        '
      properties:
        id:
          type: string
          description: A unique identifier for the completion.
        choices:
          type: array
          description: The list of completion choices the model generated for the input prompt.
          items:
            type: object
            required:
            - finish_reason
            - index
            - logprobs
            - text
            properties:
              finish_reason:
                type: string
                description: 'The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence,

                  `length` if the maximum number of tokens specified in the request was reached,

                  or `content_filter` if content was omitted due to a flag from our content filters.

                  '
                enum:
                - stop
                - length
                - content_filter
              index:
                type: integer
              logprobs:
                type: object
                nullable: true
                properties:
                  text_offset:
                    type: array
                    items:
                      type: integer
                  token_logprobs:
                    type: array
                    items:
                      type: number
                  tokens:
                    type: array
                    items:
                      type: string
                  top_logprobs:
                    type: array
                    items:
                      type: object
                      additionalProperties:
                        type: number
              text:
                type: string
        created:
          type: integer
          description: The Unix timestamp (in seconds) of when the completion was created.
        model:
          type: string
          description: The model used for completion.
        system_fingerprint:
          type: string
          description: 'This fingerprint represents the backend configuration that the model runs with.


            Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.

            '
        object:
          type: string
          description: The object type, which is always "text_completion"
          enum:
          - text_completion
        usage:
          $ref: '#/components/schemas/CompletionUsage'
      required:
      - id
      - object
      - created
      - model
      - choices
      x-oaiMeta:
        name: The completion object
        legacy: true
        example: "{\n  \"id\": \"cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7\",\n  \"object\": \"text_completion\",\n  \"created\": 1589478378,\n  \"model\": \"gpt-3.5-turbo\",\n  \"choices\": [\n    {\n      \"text\": \"\\n\\nThis is indeed a test\",\n      \"index\": 0,\n      \"logprobs\": null,\n      \"finish_reason\": \"length\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 5,\n    \"completion_tokens\": 7,\n    \"total_tokens\": 12\n  }\n}\n"
    ChatCompletionStreamOptions:
      anyOf:
      - description: 'Options for streaming response. Only set this when you set `stream: true`.

          '
        type: object
        default: null
        properties:
          include_usage:
            type: boolean
            description: 'If set, an additional chunk will be streamed before the `data: [DONE]`

              message. The `usage` field on this chunk shows the token usage statistics

              for the entire request, and the `choices` field will always be an empty

              array.


              All other chunks will also include a `usage` field, but with a null

              value. **NOTE:** If the stream is interrupted, you may not receive the

              final usage chunk which contains the total token usage for the request.

              '
          include_obfuscation:
            type: boolean
            description: 'When true, stream obfuscation will be enabled. Stream obfuscation adds

              random characters to an `obfuscation` field on streaming delta events to

              normalize payload sizes as a mitigation to certain side-channel attacks.

              These obfuscation fields are included by default, but add a small amount

              of overhead to the data stream. You can set `include_obfuscation` to

              false to optimize for bandwidth if you trust the network links between

              your application and the OpenAI API.

              '
      - type: 'null'
    CreateCompletionRequest:
      type: object
      properties:
        model:
          description: 'ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them.

            '
          anyOf:
          - type: string
          - type: string
            enum:
            - gpt-3.5-turbo-instruct
            - davinci-002
            - babbage-002
          x-oaiTypeLabel: string
        prompt:
          description: '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.

            '
          default: <|endoftext|>
          nullable: true
          oneOf:
          - type: string
            default: ''
            example: This is a test.
          - type: array
            items:
              type: string
              default: ''
              example: This is a test.
          - type: array
            minItems: 1
            items:
              type: integer
            example: '[1212, 318, 257, 1332, 13]'
          - type: array
            minItems: 1
            items:
              type: array
              minItems: 1
              items:
                type: integer
            example: '[[1212, 318, 257, 1332, 13]]'
        best_of:
          type: integer
          default: 1
          minimum: 0
          maximum: 20
          nullable: true
          description: '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`.

            '
        echo:
          type: boolean
          default: false
          nullable: true
          description: 'Echo back the prompt in addition to the completion

            '
        frequency_penalty:
          type: number
          default: 0
          minimum: -2
          maximum: 2
          nullable: true
          description: '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.


            [See more information about frequency and presence penalties.](/docs/guides/text-generation)

            '
        logit_bias:
          type: object
          x-oaiTypeLabel: map
          default: null
          nullable: true
          additionalProperties:
            type: integer
          description: '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](/tokenizer?view=bpe) 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.


            As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated.

            '
        logprobs:
          type: integer
          minimum: 0
          maximum: 5
          default: null
          nullable: true
          description: '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.

            '
        max_tokens:
          type: integer
          minimum: 0
          default: 16
          example: 16
          nullable: true
          description: 'The maximum number of [tokens](/tokenizer) that can be generated in the completion.


            The token count of your prompt plus `max_tokens` cannot exceed the model''s context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.

            '
        n:
          type: integer
          minimum: 1
          maximum: 128
          default: 1
          example: 1
          nullable: true
          description: '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`.

            '
        presence_penalty:
          type: number
          default: 0
          minimum: -2
          maximum: 2
          nullable: true
          description: '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.


            [See more information about frequency and presence penalties.](/docs/guides/text-generation)

            '
        seed:
          type: integer
          format: int64
          nullable: true
          description: '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.

            '
        stop:
          $ref: '#/components/schemas/StopConfiguration'
        stream:
          description: 'Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).

            '
          type: boolean
          nullable: true
          default: false
        stream_options:
          $ref: '#/components/schemas/ChatCompletionStreamOptions'
        suffix:
          description: 'The suffix that comes after a completion of inserted text.


            This parameter is only supported for `gpt-3.5-turbo-instruct`.

            '
          default: null
          nullable: true
          type: string
          example: test.
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 1
          example: 1
          nullable: true
          description: '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.

            '
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          example: 1
          nullable: true
          description: '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.

            '
        user:
          type: string
          example: user-1234
          description: 'A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids).

            '
      required:
      - model
      - prompt
  securitySchemes:
    ApiKeyAuth:
      type: http
      scheme: bearer
x-oaiMeta:
  groups:
  - id: audio
    title: Audio
    description: 'Learn how to turn audio into text or text into audio.


      Related guide: [Speech to text](/docs/guides/speech-to-text)

      '
    sections:
    - type: endpoint
      key: createSpeech
      path: createSpeech
    - type: endpoint
      key: createTranscription
      path: createTranscription
    - type: endpoint
      key: createTranslation
      path: createTranslation
  - id: chat
    title: Chat
    description: 'Given a list of messages comprising a conversation, the model will return a response.


      Related guide: [Chat Completions](/docs/guides/text-generation)

      '
    sections:
    - type: endpoint
      key: createChatCompletion
      path: create
    - type: object
      key: CreateChatCompletionResponse
      path: object
    - type: object
      key: CreateChatCompletionStreamResponse
      path: streaming
  - id: embeddings
    title: Embeddings
    description: 'Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.


      Related guide: [Embeddings](/docs/guides/embeddings)

      '
    sections:
    - type: endpoint
      key: createEmbedding
      path: create
    - type: object
      key: Embedding
      path: object
  - id: fine-tuning
    title: Fine-tuning
    description: 'Manage fine-tuning jobs to tailor a model to your specific training data.


      Related guide: [Fine-tune models](/docs/guides/fine-tuning)

      '
    sections:
    - type: endpoint
      key: createFineTuningJob
      path: create
    - type: endpoint
      key: listPaginatedFineTuningJobs
      path: list
    - type: endpoint
      key: listFineTuningEvents
      path: list-events
    - type: endpoint
      key: retrieveFineTuningJob
      path: retrieve
    - type: endpoint
      key: cancelFineTuningJob
      path: cancel
    - type: object
      key: FineTuningJob
      path: object
    - type: object
      key: FineTuningJobEvent
      path: event-object
  - id: files
    title: Files
    description: 'Files are used to upload documents that can be used with features like [Assistants](/docs/api-reference/assistants) and [Fine-tuning](/docs/api-reference/fine-tuning).

      '
    sections:
    - type: endpoint
      key: createFile
      path: create
    - type: endpoint
      key: listFiles
      path: list
    - type: endpoint
      key: retrieveFile
      path: retrieve
    - type: endpoint
      key: deleteFile
      path: delete
    - type: endpoint
      key: downloadFile
      path: retrieve-contents
    - type: object
      key: OpenAIFile
      path: object
  - id: images
    title: Images
    description: 'Given a prompt and/or an input image, the model will generate a new image.


      Related guide: [Image generation](/docs/guides/images)

      '
    sections:
    - type: endpoint
      key: createImage
      path: create
    - type: endpoint
      key: createImageEdit
      path: createEdit
    - type: endpoint
      key: createImageVariation
      path: createVariation
    - type: object
      key: Image
      path: object
  - id: models
    title: Models
    description: 'List and describe the various models available in the API. You can refer to the [Models](/docs/models) documentation to understand what models are available and the differences between them.

      '
    sections:
    - type: endpoint
      key: listModels
      path: list
    - type: endpoint
      key: retrieveModel
      path: retrieve
    - type: endpoint
      key: deleteModel
      path: delete
    - type: object
      key: Model
      path: object
  - id: moderations
    title: Moderations
    description: 'Given a input text, outputs if the model classifies it as violating OpenAI''s content policy.


      Related guide: [Moderations](/docs/guides/moderation)

      '
    sections:
    - type: endpoint
      key: createModeration
      path: create
    - type: object
      key: CreateModerationResponse
      path: object
  - id: assistants
    title: Assistants
    beta: true
    description: 'Build assistants that can call models and use tools to perform tasks.


      [Get started with the Assistants API](/docs/assistants)

      '
    sections:
    - type: endpoint
      key: createAssistant
      path: createAssistant
    - type: endpoint
      key: createAssistantFile
      path: createAssistantFile
    - type: endpoint
      key: listAssistants
      path: listAssistants
    - type: endpoint
      key: listAssistantFiles
      path: listAssistantFiles
    - type: endpoint
      key: getAssistant
      path: getAssistant
    - type: endpoint
      key: getAssistantFile
      path: getAssistantFile
    - type: endpoint
      key: modifyAssistant
      path: modifyAssistant
    - type: endpoint
      key: deleteAssistant
      path: deleteAssistant
    - type: endpoint
      key: deleteAssistantFile
      path: deleteAssistantFile
    - type: object
      key: AssistantObject
      path: object
    - type: object
      key: AssistantFileObject
      path: file-object
  - id: threads
    title: Threads
    beta: true
    description: 'Create threads that assistants can interact with.


      Related guide: [Assistants](/docs/assistants/overview)

      '
    sections:
    - type: endpoint
      key: createThread
      path: createThread
    - type: endpoint
      key: getThread
      path: getThread
    - type: endpoint
      key: modifyThread
      path: modifyThread
    - type: endpoint
      key: deleteThread
      path: deleteThread
    - type: object
      key: ThreadObject
      path: object
  - id: messages
    title: Messages
    beta: true
    description: 'Create messages within threads


      Related guide: [Assistants](/docs/assistants/overview)

      '
    sections:
    - type: endpoint
      key: createMessage
      path: createMessage
    - type: endpoint
      key: listMessages
      path: listMessages
    - type: endpoint
      key: listMessageFiles
      path: listMessageFiles
    - type: endpoint
      key: getMessage
      path: getMessage
    - type: endpoint
      key: getMessageFile
      path: getMessageFile
    - type: endpoint
      key: modifyMessage
      path: modifyMessage
    - type: object
      key: MessageObject
      path: object
    - type: object
      key: MessageFileObject
      path: file-object
  - id: runs
    title: Runs
    beta: true
    description: 'Represents an execution run on a thread.


      Related guide: [Assistants](/docs/assistants/overview)

      '
    sections:
    - type: endpoint
      key: createRun
      path: createRun
    - type: endpoint
      key: createThreadAndRun
      path: createThreadAndRun
    - type: endpoint
      key: listRuns
      path: listRuns
    - type: endpoint
      key: listRunSteps
      path: listRunSteps
    - type: endpoint
      key: getRun
      path: getRun
    - type: endpoint
      key: getRunStep
      path: getRunStep
    - type: endpoint
      key: modifyRun
      path: modifyRun
    - type: endpoint
      key: submitToolOuputsToRun
      path: submitToolOutputs
    - type: endpoint
      key: cancelRun
      path: cancelRun
    - type: object
      key: RunObject
      path: object
    - type: object
      key: RunStepObject
      path: step-object
  - id: completions
    title: Completions
    legacy: true
    description: 'Given a prompt, the model will return one or more predicted completions along with the probabilities of alternative tokens at each position. Most developer should use our [Chat Completions API](/docs/guides/text-generation/text-generation-models) to leverage our best and newest models. Most models that support the legacy Completions endpoint [will be shut off on January 4th, 2024](/docs/deprecations/2023-07-06-gpt-and-embeddings).

      '
    sections:
    - type: endpoint
      key: createCompletion
      path: create
    - type: object
      key: CreateCompletionResponse
      path: object