Post chatcompletions

Creates a chat completion.

POST /chat/completions

Error

A valid request URL is required to generate request examples

200

{
  "id": "<string>",
  "created": 123,
  "model": "<string>",
  "object": "chat.completion",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 123,
      "logprobs": {
        "content": [
          {
            "token": "<string>",
            "logprob": 123,
            "bytes": [
              123
            ],
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ]
          }
        ],
        "refusal": [
          {
            "token": "<string>",
            "logprob": 123,
            "bytes": [
              123
            ],
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ]
          }
        ]
      },
      "message": {
        "content": "<string>",
        "refusal": "<string>",
        "role": "assistant",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ],
        "annotations": [
          {
            "type": "url_citation",
            "url_citation": {
              "end_index": 123,
              "start_index": 123,
              "url": "<string>",
              "title": "<string>"
            }
          }
        ],
        "audio": {
          "id": "<string>",
          "expires_at": 123,
          "data": "aSDinaTvuI8gbWludGxpZnk=",
          "transcript": "<string>"
        },
        "context": {
          "intent": "<string>",
          "citations": [
            {
              "content": "<string>",
              "title": "<string>",
              "url": "<string>",
              "filepath": "<string>",
              "chunk_id": "<string>",
              "rerank_score": 123
            }
          ]
        },
        "reasoning_content": "<string>"
      },
      "content_filter_results": {}
    }
  ],
  "system_fingerprint": "<string>",
  "prompt_filter_results": [
    {
      "prompt_index": 123,
      "content_filter_results": {
        "prompt_index": 123
      }
    }
  ]
}

Authorizations

ApiKeyAuthApiKeyAuth_OAuth2Auth

api-key · string · header · required

Query Parameters

api-version · enum<string> · default: v1

The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Available options: v1, preview

Body

application/json

The extended request model for chat completions against the Azure OpenAI service. This adds the ability to provide data sources for the On Your Data feature.

messages · object[] · required

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

Minimum array length: 1

Show child attributes

model · string · required

The model deployment identifier to use for the chat completion request.

metadata · object

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Show child attributes

temperature · number<float> | null · default: 1

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.

Required range: 0 <= x <= 2

top_p · number<float> | null · default: 1

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.

Required range: 0 <= x <= 1

user · string

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

top_logprobs · integer<int32>

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.

Required range: 0 <= x <= 20

modalities · any

reasoning_effort · enum<string> · default: medium

o-series models only

Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Available options: low, medium, high

max_completion_tokens · integer<int32> | null

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

frequency_penalty · number<float> | null · default: 0

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.

Required range: -2 <= x <= 2

presence_penalty · number<float> | null · default: 0

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.

Required range: -2 <= x <= 2

response_format · object

An object specifying the format that the model must output.

Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema.

Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

Show child attributes

audio · object

Parameters for audio output. Required when audio output is requested with modalities: ["audio"].

Show child attributes

store · boolean | null · default: false

Whether or not to store the output of this chat completion request for use in model distillation or evals products.

stream · boolean | null · default: false

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

stop · string string[]

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.

logit_bias · object

Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. 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.

Show child attributes

logprobs · boolean | null · default: false

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

max_tokens · integer<int32> | null · deprecated

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

This value is now deprecated in favor of max_completion_tokens, and is not compatible with o1 series models.

n · integer<int32> | null · default: 1

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

Required range: 1 <= x <= 128

prediction · object

Configuration for a predicted output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.

Show child attributes

seed · integer<int64> | null

This feature is in Beta. 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.

Required range: -9223372036854776000 <= x <= 9223372036854776000

stream_options · object

Options for streaming response. Only set this when you set stream: true.

Show child attributes

tools · object[]

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.

Show child attributes

tool_choice · enum<string> object

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

none is the default when no tools are present. auto is the default if tools are present.

Available options: none, auto, required

parallel_tool_calls · boolean · default: true

Whether to enable parallel function calling during tool use.

function_call · enum<string> object · deprecated

Deprecated in favor of tool_choice.

Controls which (if any) function is called by the model.

none means the model will not call a function and instead generates a message.

auto means the model can pick between generating a message or calling a function.

Specifying a particular function via {"name": "my_function"} forces the model to call that function.

none is the default when no functions are present. auto is the default if functions are present.

Available options: none, auto

functions · object[] · deprecated

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

Required array length: 1 - 128 elements

Show child attributes

data_sources · object[]

The data sources to use for the On Your Data feature, exclusive to Azure OpenAI.

Show child attributes

user_security_context · object

User security context contains several parameters that describe the application itself, and the end user that interacts with the application. These fields assist your security operations teams to investigate and mitigate security incidents by providing a comprehensive approach to protecting your AI applications. Learn more about protecting AI applications using Microsoft Defender for Cloud.

Show child attributes

Response

200

application/json

The request has succeeded.

The extended top-level chat completion response model for the Azure OpenAI service. This model adds Responsible AI content filter annotations for prompt input.

id · string · required

A unique identifier for the chat completion.

created · integer<unixtime> · required

The Unix timestamp (in seconds) of when the chat completion was created.

model · string · required

The model used for the chat completion.

object · enum<string> · required

The object type, which is always chat.completion.

Available options: chat.completion

choices · object[] · required

Show child attributes

system_fingerprint · string

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.

usage · object

Usage statistics for the completion request.

Show child attributes

prompt_filter_results · object[]

The Responsible AI content filter annotations associated with prompt inputs into chat completions.

Show child attributes