{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/microsoft-azure-openai/json-schema/microsoft-azure-openai-create-completion-request-schema.json",
  "title": "createCompletionRequest",
  "x-generated": "2026-11-12",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/microsoft-azure-openai-deployments-api-openapi.yml#/components/schemas/createCompletionRequest",
  "type": "object",
  "properties": {
    "prompt": {
      "description": "The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.\n\nNote 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.\n",
      "default": "<|endoftext|>",
      "oneOf": [
        {
          "type": "string",
          "default": ""
        },
        {
          "type": "array",
          "items": {
            "type": "string",
            "default": ""
          }
        }
      ]
    },
    "best_of": {
      "type": [
        "integer",
        "null"
      ],
      "default": 1,
      "minimum": 0,
      "maximum": 20,
      "description": "Generates `best_of` completions server-side and returns the \"best\" (the one with the highest log probability per token). Results cannot be streamed.\n\nWhen used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return â€“ `best_of` must be greater than `n`.\n\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`.\n"
    },
    "echo": {
      "type": [
        "boolean",
        "null"
      ],
      "default": false,
      "description": "Echo back the prompt in addition to the completion\n"
    },
    "frequency_penalty": {
      "type": [
        "number",
        "null"
      ],
      "default": 0,
      "minimum": -2,
      "maximum": 2,
      "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.\n"
    },
    "logit_bias": {
      "type": [
        "object",
        "null"
      ],
      "x-oaiTypeLabel": "map",
      "default": null,
      "additionalProperties": {
        "type": "integer"
      },
      "description": "Modify the likelihood of specified tokens appearing in the completion.\n\nAccepts 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](https://platform.openai.com/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.\n\nAs an example, you can pass `{\"50256\": -100}` to prevent the <|endoftext|> token from being generated.\n"
    },
    "logprobs": {
      "type": [
        "integer",
        "null"
      ],
      "minimum": 0,
      "maximum": 5,
      "default": null,
      "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.\n\nThe maximum value for `logprobs` is 5.\n"
    },
    "max_tokens": {
      "type": [
        "integer",
        "null"
      ],
      "minimum": 0,
      "default": 16,
      "description": "The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the completion.\n\nThe 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"
    },
    "n": {
      "type": [
        "integer",
        "null"
      ],
      "minimum": 1,
      "maximum": 128,
      "default": 1,
      "description": "How many completions to generate for each prompt.\n\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`.\n"
    },
    "presence_penalty": {
      "type": [
        "number",
        "null"
      ],
      "default": 0,
      "minimum": -2,
      "maximum": 2,
      "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.\n"
    },
    "seed": {
      "type": [
        "integer",
        "null"
      ],
      "minimum": -9223372036854775808,
      "maximum": 9223372036854775807,
      "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.\n\nDeterminism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.\n"
    },
    "stop": {
      "description": "Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.\n",
      "default": null,
      "oneOf": [
        {
          "type": [
            "string",
            "null"
          ],
          "default": "<|endoftext|>"
        },
        {
          "type": "array",
          "minItems": 1,
          "maxItems": 4,
          "items": {
            "type": "string"
          }
        }
      ]
    },
    "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).\n",
      "type": [
        "boolean",
        "null"
      ],
      "default": false
    },
    "suffix": {
      "description": "The suffix that comes after a completion of inserted text.\n\nThis parameter is only supported for `gpt-3.5-turbo-instruct`.\n",
      "default": null,
      "type": [
        "string",
        "null"
      ]
    },
    "temperature": {
      "type": [
        "number",
        "null"
      ],
      "minimum": 0,
      "maximum": 2,
      "default": 1,
      "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.\n\nWe generally recommend altering this or `top_p` but not both.\n"
    },
    "top_p": {
      "type": [
        "number",
        "null"
      ],
      "minimum": 0,
      "maximum": 1,
      "default": 1,
      "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.\n\nWe generally recommend altering this or `temperature` but not both.\n"
    },
    "user": {
      "type": "string",
      "description": "A unique identifier representing your end-user, which can help to monitor and detect abuse.\n"
    }
  },
  "required": [
    "prompt"
  ]
}