Azure OpenAI API (preview:2024-04-01)

2025/03/21 • 2 updated methods

GetChatCompletions (updated)
Description :  Gets chat completions for the provided chat messages. Completions support a wide variety of tasks and generate text that continues from or "completes" provided prompt data.
Reference :  Link ¶

⚶ Changes

{
  "#id": "GetChatCompletions",
  "$responses": {
    "200": {
      "$properties": [
        {
          "#name": "usage",
          "Required": {
            "new": false,
            "old": true
          }
        }
      ]
    }
  }
}

⚼ Request

POST:  /deployments/{deploymentId}/chat/completions
{
api-version:
{
Description: The API version to use for this operation. ,
Required: True ,
}
string ,
deploymentId:
{
Description: Specifies either the model deployment name (when using Azure OpenAI) or model name (when using non-Azure OpenAI) to use for this request. ,
Required: True ,
}
string ,
body:
{
Description: The configuration information for a chat completions request. Completions support a wide variety of tasks and generate text that continues from or "completes" provided prompt data. ,
Required: True ,
}
{
messages:
{
Description: The collection of context messages associated with this chat completions request. Typical usage begins with a chat message for the System role that provides instructions for the behavior of the assistant, followed by alternating messages between the User and Assistant roles. ,
Required: True ,
}
[
{
role:
{
Description: The chat role associated with this message. ,
Enum:
{
system: The role that instructs or sets the behavior of the assistant. ,
assistant: The role that provides responses to system-instructed, user-prompted input. ,
user: The role that provides input for chat completions. ,
function: The role that provides function results for chat completions. ,
tool: The role that represents extension tool activity within a chat completions operation. ,
}
,
Required: True ,
}
enum ,
}
,
]
,
functions:
{
Description: A list of functions the model may generate JSON inputs for. ,
Required: False ,
}
[
{
name:
{
Description: The name of the function to be called. ,
Required: True ,
}
string ,
description:
{
Description: A description of what the function does. The model will use this description when selecting the function and interpreting its parameters. ,
Required: False ,
}
string ,
parameters:
{
Description: The parameters the function accepts, described as a JSON Schema object. ,
Required: False ,
}
string ,
}
,
]
,
function_call:
{
Description: Controls how the model responds to function calls. "none" means the model does not call a function, and responds to the end-user. "auto" means the model can pick between an end-user 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. ,
Required: False ,
}
string ,
max_tokens:
{
Description: The maximum number of tokens allowed for the generated answer. By default, the number of tokens the model can return will be (4096 - prompt tokens). This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with o1 series models. ,
Format: int32 ,
Required: False ,
}
integer ,
temperature:
{
Description: The sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict. ,
Format: float ,
Required: False ,
}
number ,
top_p:
{
Description: An alternative to sampling with temperature called nucleus sampling. This value causes the model to consider the results of tokens with the provided probability mass. As an example, a value of 0.15 will cause only the tokens comprising the top 15% of probability mass to be considered. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict. ,
Format: float ,
Required: False ,
}
number ,
logit_bias:
{
Description: A map between GPT token IDs and bias scores that influences the probability of specific tokens appearing in a completions response. Token IDs are computed via external tokenizer tools, while bias scores reside in the range of -100 to 100 with minimum and maximum values corresponding to a full ban or exclusive selection of a token, respectively. The exact behavior of a given bias score varies by model. ,
Required: False ,
}
object ,
user:
{
Description: An identifier for the caller or end user of the operation. This may be used for tracking or rate-limiting purposes. ,
Required: False ,
}
string ,
n:
{
Description: The number of chat completions choices that should be generated for a chat completions response. Because this setting can generate many completions, it may quickly consume your token quota. Use carefully and ensure reasonable settings for max_tokens and stop. ,
Format: int32 ,
Required: False ,
}
integer ,
stop:
{
Description: A collection of textual sequences that will end completions generation. ,
Required: False ,
}
[
string ,
]
,
presence_penalty:
{
Description: A value that influences the probability of generated tokens appearing based on their existing presence in generated text. Positive values will make tokens less likely to appear when they already exist and increase the model's likelihood to output new topics. ,
Format: float ,
Required: False ,
}
number ,
frequency_penalty:
{
Description: A value that influences the probability of generated tokens appearing based on their cumulative frequency in generated text. Positive values will make tokens less likely to appear as their frequency increases and decrease the likelihood of the model repeating the same statements verbatim. ,
Format: float ,
Required: False ,
}
number ,
stream:
{
Description: A value indicating whether chat completions should be streamed for this request. ,
Required: False ,
}
boolean ,
model:
{
Description: The model name to provide as part of this completions request. Not applicable to Azure OpenAI, where deployment information should be included in the Azure resource URI that's connected to. ,
Required: False ,
}
string ,
data_sources:
{
Description: The configuration entries for Azure OpenAI chat extensions that use them. This additional specification is only compatible with Azure OpenAI. ,
Required: False ,
}
[
{
type:
{
Description: The label for the type of an Azure chat extension. This typically corresponds to a matching Azure resource. Azure chat extensions are only compatible with Azure OpenAI. ,
Enum:
{
azure_search: Represents the use of Azure AI Search as an Azure OpenAI chat extension. ,
azure_ml_index: Represents the use of Azure Machine Learning index as an Azure OpenAI chat extension. ,
azure_cosmos_db: Represents the use of Azure Cosmos DB as an Azure OpenAI chat extension. ,
elasticsearch: Represents the use of Elasticsearch® index as an Azure OpenAI chat extension. ,
pinecone: Represents the use of Pinecone index as an Azure OpenAI chat extension. ,
}
,
Required: True ,
}
enum ,
}
,
]
,
enhancements:
{
Description: If provided, the configuration options for available Azure OpenAI chat enhancements. ,
Required: False ,
}
{
grounding:
{
Description: A representation of the available options for the Azure OpenAI grounding enhancement. ,
Required: False ,
}
{
enabled:
{
Description: Specifies whether the enhancement is enabled. ,
Required: True ,
}
boolean ,
}
,
ocr:
{
Description: A representation of the available options for the Azure OpenAI optical character recognition (OCR) enhancement. ,
Required: False ,
}
{
enabled:
{
Description: Specifies whether the enhancement is enabled. ,
Required: True ,
}
boolean ,
}
,
}
,
seed:
{
Description: If specified, the 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." ,
Format: int64 ,
Required: False ,
}
integer ,
logprobs:
{
Description: 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`. This option is currently not available on the `gpt-4-vision-preview` model. ,
Required: False ,
}
boolean ,
top_logprobs:
{
Description: An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. ,
Format: int32 ,
Required: False ,
}
integer ,
response_format:
{
Description: An object specifying the format that the model must output. Used to enable JSON mode. ,
Required: False ,
}
{
type:
{
Description: The discriminated type for the response format. ,
Required: True ,
}
string ,
}
,
tools:
{
Description: The available tool definitions that the chat completions request can use, including caller-defined functions. ,
Required: False ,
}
[
{
type:
{
Description: The object type. ,
Required: True ,
}
string ,
}
,
]
,
tool_choice:
{
Description: If specified, the model will configure which of the provided tools it can use for the chat completions response. ,
Required: False ,
}
string ,
}
,
}

⚐ Response (200)

{
id:
{
Description: A unique identifier associated with this chat completions response. ,
Required: True ,
}
string ,
created:
{
Description: The first timestamp associated with generation activity for this completions response, represented as seconds since the beginning of the Unix epoch of 00:00 on 1 Jan 1970. ,
Format: unixtime ,
Required: True ,
}
integer ,
choices:
{
Description: The collection of completions choices associated with this completions response. Generally, `n` choices are generated per provided prompt with a default value of 1. Token limits and other settings may limit the number of choices generated. ,
Required: True ,
}
[
{
message:
{
Description: The chat message for a given chat completions prompt. ,
Required: False ,
}
{
role:
{
Description: The chat role associated with the message. ,
Enum:
{
system: The role that instructs or sets the behavior of the assistant. ,
assistant: The role that provides responses to system-instructed, user-prompted input. ,
user: The role that provides input for chat completions. ,
function: The role that provides function results for chat completions. ,
tool: The role that represents extension tool activity within a chat completions operation. ,
}
,
Required: True ,
}
enum ,
content:
{
Description: The content of the message. ,
Required: True ,
}
string ,
tool_calls:
{
Description: The tool calls that must be resolved and have their outputs appended to subsequent input messages for the chat completions request to resolve as configured. ,
Required: False ,
}
[
{
type:
{
Description: The object type. ,
Required: True ,
}
string ,
id:
{
Description: The ID of the tool call. ,
Required: True ,
}
string ,
}
,
]
,
function_call:
{
Description: The function call that must be resolved and have its output appended to subsequent input messages for the chat completions request to resolve as configured. ,
Required: False ,
}
{
name:
{
Description: The name of the function to call. ,
Required: True ,
}
string ,
arguments:
{
Description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. ,
Required: True ,
}
string ,
}
,
context:
{
Description: If Azure OpenAI chat extensions are configured, this array represents the incremental steps performed by those extensions while processing the chat completions request. ,
Required: False ,
}
{
citations:
{
Description: The contextual information associated with the Azure chat extensions used for a chat completions request. These messages describe the data source retrievals, plugin invocations, and other intermediate steps taken in the course of generating a chat completions response that was augmented by capabilities from Azure OpenAI chat extensions. ,
Required: False ,
}
[
{
content:
{
Description: The content of the citation. ,
Required: True ,
}
string ,
title:
{
Description: The title of the citation. ,
Required: False ,
}
string ,
url:
{
Description: The URL of the citation. ,
Required: False ,
}
string ,
filepath:
{
Description: The file path of the citation. ,
Required: False ,
}
string ,
chunk_id:
{
Description: The chunk ID of the citation. ,
Required: False ,
}
string ,
rerank_score:
{
Description: The rerank score of the retrieved document. ,
Format: double ,
Required: False ,
}
number ,
}
,
]
,
intent:
{
Description: The detected intent from the chat history, used to pass to the next turn to carry over the context. ,
Required: False ,
}
string ,
}
,
}
,
logprobs:
{
Description: The log probability information for this choice, as enabled via the 'logprobs' request option. ,
Required: True ,
}
object ,
index:
{
Description: The ordered index associated with this chat completions choice. ,
Format: int32 ,
Required: True ,
}
integer ,
finish_reason:
{
Description: The reason that this chat completions choice completed its generated. ,
Enum:
{
stop: Completions ended normally and reached its end of token generation. ,
length: Completions exhausted available token limits before generation could complete. ,
content_filter: Completions generated a response that was identified as potentially sensitive per content moderation policies. ,
function_call: Completion ended normally, with the model requesting a function to be called. ,
tool_calls: Completion ended with the model calling a provided tool for output. ,
}
,
Required: True ,
}
enum ,
finish_details:
{
Description: The reason the model stopped generating tokens, together with any applicable details. This structured representation replaces 'finish_reason' for some models. ,
Required: False ,
}
{
type:
{
Description: The object type. ,
Required: True ,
}
string ,
}
,
delta:
{
Description: The delta message content for a streaming response. ,
Required: False ,
}
{
role:
{
Description: The chat role associated with the message. ,
Enum:
{
system: The role that instructs or sets the behavior of the assistant. ,
assistant: The role that provides responses to system-instructed, user-prompted input. ,
user: The role that provides input for chat completions. ,
function: The role that provides function results for chat completions. ,
tool: The role that represents extension tool activity within a chat completions operation. ,
}
,
Required: True ,
}
enum ,
content:
{
Description: The content of the message. ,
Required: True ,
}
string ,
tool_calls:
{
Description: The tool calls that must be resolved and have their outputs appended to subsequent input messages for the chat completions request to resolve as configured. ,
Required: False ,
}
[
{
type:
{
Description: The object type. ,
Required: True ,
}
string ,
id:
{
Description: The ID of the tool call. ,
Required: True ,
}
string ,
}
,
]
,
function_call:
{
Description: The function call that must be resolved and have its output appended to subsequent input messages for the chat completions request to resolve as configured. ,
Required: False ,
}
{
name:
{
Description: The name of the function to call. ,
Required: True ,
}
string ,
arguments:
{
Description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. ,
Required: True ,
}
string ,
}
,
context:
{
Description: If Azure OpenAI chat extensions are configured, this array represents the incremental steps performed by those extensions while processing the chat completions request. ,
Required: False ,
}
{
citations:
{
Description: The contextual information associated with the Azure chat extensions used for a chat completions request. These messages describe the data source retrievals, plugin invocations, and other intermediate steps taken in the course of generating a chat completions response that was augmented by capabilities from Azure OpenAI chat extensions. ,
Required: False ,
}
[
{
content:
{
Description: The content of the citation. ,
Required: True ,
}
string ,
title:
{
Description: The title of the citation. ,
Required: False ,
}
string ,
url:
{
Description: The URL of the citation. ,
Required: False ,
}
string ,
filepath:
{
Description: The file path of the citation. ,
Required: False ,
}
string ,
chunk_id:
{
Description: The chunk ID of the citation. ,
Required: False ,
}
string ,
rerank_score:
{
Description: The rerank score of the retrieved document. ,
Format: double ,
Required: False ,
}
number ,
}
,
]
,
intent:
{
Description: The detected intent from the chat history, used to pass to the next turn to carry over the context. ,
Required: False ,
}
string ,
}
,
}
,
content_filter_results:
{
Description: Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. ,
Required: False ,
}
{
sexual:
{
Description: Describes language related to anatomical organs and genitals, romantic relationships, acts portrayed in erotic or affectionate terms, physical sexual acts, including those portrayed as an assault or a forced sexual violent act against one’s will, prostitution, pornography, and abuse. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
violence:
{
Description: Describes language related to physical actions intended to hurt, injure, damage, or kill someone or something; describes weapons, etc. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
hate:
{
Description: Describes language attacks or uses that include pejorative or discriminatory language with reference to a person or identity group on the basis of certain differentiating attributes of these groups including but not limited to race, ethnicity, nationality, gender identity and expression, sexual orientation, religion, immigration status, ability status, personal appearance, and body size. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
self_harm:
{
Description: Describes language related to physical actions intended to purposely hurt, injure, or damage one’s body, or kill oneself. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
profanity:
{
Description: Describes whether profanity was detected. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
custom_blocklists:
{
Description: Describes detection results against configured custom blocklists. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
details:
{
Description: The collection of detailed blocklist result information. ,
Required: False ,
}
[
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
id:
{
Description: The ID of the custom blocklist evaluated. ,
Required: True ,
}
string ,
}
,
]
,
}
,
error:
{
Description: Describes an error returned if the content filtering system is down or otherwise unable to complete the operation in time. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: True ,
}
string ,
message:
{
Description: A human-readable representation of the error. ,
Required: True ,
}
string ,
target:
{
Description: The target of the error. ,
Required: False ,
}
string ,
details:
{
Description: An array of details about specific errors that led to this reported error. ,
Required: False ,
}
[
string ,
]
,
innererror:
{
Description: An object containing more specific information than the current object about the error. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: False ,
}
string ,
innererror:
{
Required: False ,
}
string ,
}
,
}
,
protected_material_text:
{
Description: Information about detection of protected text material. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
protected_material_code:
{
Description: Information about detection of protected code material. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
URL:
{
Description: The internet location associated with the detection. ,
Format: uri ,
Required: False ,
}
string ,
license:
{
Description: The license description associated with the detection. ,
Required: False ,
}
string ,
}
,
}
,
enhancements:
{
Description: Represents the output results of Azure OpenAI enhancements to chat completions, as configured via the matching input provided in the request. This supplementary information is only available when using Azure OpenAI and only when the request is configured to use enhancements. ,
Required: False ,
}
{
grounding:
{
Description: The grounding enhancement that returns the bounding box of the objects detected in the image. ,
Required: False ,
}
{
lines:
{
Description: The lines of text detected by the grounding enhancement. ,
Required: True ,
}
[
{
text:
{
Description: The text within the line. ,
Required: True ,
}
string ,
spans:
{
Description: An array of spans that represent detected objects and its bounding box information. ,
Required: True ,
}
[
{
text:
{
Description: The text content of the span that represents the detected object. ,
Required: True ,
}
string ,
offset:
{
Description: The character offset within the text where the span begins. This offset is defined as the position of the first character of the span, counting from the start of the text as Unicode codepoints. ,
Format: int32 ,
Required: True ,
}
integer ,
length:
{
Description: The length of the span in characters, measured in Unicode codepoints. ,
Format: int32 ,
Required: True ,
}
integer ,
polygon:
{
Description: An array of objects representing points in the polygon that encloses the detected object. ,
Required: True ,
}
[
{
x:
{
Description: The x-coordinate (horizontal axis) of the point. ,
Format: float ,
Required: True ,
}
number ,
y:
{
Description: The y-coordinate (vertical axis) of the point. ,
Format: float ,
Required: True ,
}
number ,
}
,
]
,
}
,
]
,
}
,
]
,
}
,
}
,
}
,
]
,
model:
{
Description: The model name used for this completions request. ,
Required: False ,
}
string ,
prompt_filter_results:
{
Description: Content filtering results for zero or more prompts in the request. In a streaming request, results for different prompts may arrive at different times or in different orders. ,
Required: False ,
}
[
{
prompt_index:
{
Description: The index of this prompt in the set of prompt results ,
Format: int32 ,
Required: True ,
}
integer ,
content_filter_results:
{
Description: Content filtering results for this prompt ,
Required: True ,
}
{
sexual:
{
Description: Describes language related to anatomical organs and genitals, romantic relationships, acts portrayed in erotic or affectionate terms, physical sexual acts, including those portrayed as an assault or a forced sexual violent act against one’s will, prostitution, pornography, and abuse. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
violence:
{
Description: Describes language related to physical actions intended to hurt, injure, damage, or kill someone or something; describes weapons, etc. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
hate:
{
Description: Describes language attacks or uses that include pejorative or discriminatory language with reference to a person or identity group on the basis of certain differentiating attributes of these groups including but not limited to race, ethnicity, nationality, gender identity and expression, sexual orientation, religion, immigration status, ability status, personal appearance, and body size. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
self_harm:
{
Description: Describes language related to physical actions intended to purposely hurt, injure, or damage one’s body, or kill oneself. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
profanity:
{
Description: Describes whether profanity was detected. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
custom_blocklists:
{
Description: Describes detection results against configured custom blocklists. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
details:
{
Description: The collection of detailed blocklist result information. ,
Required: False ,
}
[
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
id:
{
Description: The ID of the custom blocklist evaluated. ,
Required: True ,
}
string ,
}
,
]
,
}
,
error:
{
Description: Describes an error returned if the content filtering system is down or otherwise unable to complete the operation in time. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: True ,
}
string ,
message:
{
Description: A human-readable representation of the error. ,
Required: True ,
}
string ,
target:
{
Description: The target of the error. ,
Required: False ,
}
string ,
details:
{
Description: An array of details about specific errors that led to this reported error. ,
Required: False ,
}
[
string ,
]
,
innererror:
{
Description: An object containing more specific information than the current object about the error. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: False ,
}
string ,
innererror:
{
Required: False ,
}
string ,
}
,
}
,
jailbreak:
{
Description: Whether a jailbreak attempt was detected in the prompt. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
indirect_attack:
{
Description: Whether an indirect attack was detected in the prompt. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
}
,
}
,
]
,
system_fingerprint:
{
Description: Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. ,
Required: False ,
}
string ,
usage:
{
Description: Usage information for tokens processed and generated as part of this completions operation. ,
Required: False ,
}
{
completion_tokens:
{
Description: The number of tokens generated across all completions emissions. ,
Format: int32 ,
Required: True ,
}
integer ,
prompt_tokens:
{
Description: The number of tokens in the provided prompts for the completions request. ,
Format: int32 ,
Required: True ,
}
integer ,
total_tokens:
{
Description: The total number of tokens processed for the completions request and response. ,
Format: int32 ,
Required: True ,
}
integer ,
}
,
}

⚐ Response (default)

{
$headers:
{
x-ms-error-code:
{
Description: String error code indicating what went wrong. ,
}
string ,
}
,
$schema:
{
Description: A response containing error details. ,
}
{
error:
{
Description: The error object. ,
Required: True ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: True ,
}
string ,
message:
{
Description: A human-readable representation of the error. ,
Required: True ,
}
string ,
target:
{
Description: The target of the error. ,
Required: False ,
}
string ,
details:
{
Description: An array of details about specific errors that led to this reported error. ,
Required: False ,
}
[
string ,
]
,
innererror:
{
Description: An object containing more specific information than the current object about the error. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: False ,
}
string ,
innererror:
{
Required: False ,
}
string ,
}
,
}
,
}
,
}
GetCompletions (updated)
Description :  Gets completions for the provided input prompts. Completions support a wide variety of tasks and generate text that continues from or "completes" provided prompt data.
Reference :  Link ¶

⚶ Changes

{
  "#id": "GetCompletions",
  "$responses": {
    "200": {
      "$properties": [
        {
          "#name": "usage",
          "Required": {
            "new": false,
            "old": true
          }
        }
      ]
    }
  }
}

⚼ Request

POST:  /deployments/{deploymentId}/completions
{
api-version:
{
Description: The API version to use for this operation. ,
Required: True ,
}
string ,
deploymentId:
{
Description: Specifies either the model deployment name (when using Azure OpenAI) or model name (when using non-Azure OpenAI) to use for this request. ,
Required: True ,
}
string ,
body:
{
Description: The configuration information for a completions request. Completions support a wide variety of tasks and generate text that continues from or "completes" provided prompt data. ,
Required: True ,
}
{
prompt:
{
Description: The prompts to generate completions from. ,
Required: True ,
}
[
string ,
]
,
max_tokens:
{
Description: The maximum number of tokens to generate. ,
Format: int32 ,
Required: False ,
}
integer ,
temperature:
{
Description: The sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict. ,
Format: float ,
Required: False ,
}
number ,
top_p:
{
Description: An alternative to sampling with temperature called nucleus sampling. This value causes the model to consider the results of tokens with the provided probability mass. As an example, a value of 0.15 will cause only the tokens comprising the top 15% of probability mass to be considered. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict. ,
Format: float ,
Required: False ,
}
number ,
logit_bias:
{
Description: A map between GPT token IDs and bias scores that influences the probability of specific tokens appearing in a completions response. Token IDs are computed via external tokenizer tools, while bias scores reside in the range of -100 to 100 with minimum and maximum values corresponding to a full ban or exclusive selection of a token, respectively. The exact behavior of a given bias score varies by model. ,
Required: False ,
}
object ,
user:
{
Description: An identifier for the caller or end user of the operation. This may be used for tracking or rate-limiting purposes. ,
Required: False ,
}
string ,
n:
{
Description: The number of completions choices that should be generated per provided prompt as part of an overall completions response. Because this setting can generate many completions, it may quickly consume your token quota. Use carefully and ensure reasonable settings for max_tokens and stop. ,
Format: int32 ,
Required: False ,
}
integer ,
logprobs:
{
Description: A value that controls the emission of log probabilities for the provided number of most likely tokens within a completions response. ,
Format: int32 ,
Required: False ,
}
integer ,
suffix:
{
Description: The suffix that comes after a completion of inserted text ,
Required: False ,
}
string ,
echo:
{
Description: A value specifying whether completions responses should include input prompts as prefixes to their generated output. ,
Required: False ,
}
boolean ,
stop:
{
Description: A collection of textual sequences that will end completions generation. ,
Required: False ,
}
[
string ,
]
,
presence_penalty:
{
Description: A value that influences the probability of generated tokens appearing based on their existing presence in generated text. Positive values will make tokens less likely to appear when they already exist and increase the model's likelihood to output new topics. ,
Format: float ,
Required: False ,
}
number ,
frequency_penalty:
{
Description: A value that influences the probability of generated tokens appearing based on their cumulative frequency in generated text. Positive values will make tokens less likely to appear as their frequency increases and decrease the likelihood of the model repeating the same statements verbatim. ,
Format: float ,
Required: False ,
}
number ,
best_of:
{
Description: A value that controls how many completions will be internally generated prior to response formulation. When used together with n, best_of controls the number of candidate completions and must be greater than n. Because this setting can generate many completions, it may quickly consume your token quota. Use carefully and ensure reasonable settings for max_tokens and stop. ,
Format: int32 ,
Required: False ,
}
integer ,
stream:
{
Description: A value indicating whether chat completions should be streamed for this request. ,
Required: False ,
}
boolean ,
model:
{
Description: The model name to provide as part of this completions request. Not applicable to Azure OpenAI, where deployment information should be included in the Azure resource URI that's connected to. ,
Required: False ,
}
string ,
}
,
}

⚐ Response (200)

{
id:
{
Description: A unique identifier associated with this completions response. ,
Required: True ,
}
string ,
created:
{
Description: The first timestamp associated with generation activity for this completions response, represented as seconds since the beginning of the Unix epoch of 00:00 on 1 Jan 1970. ,
Format: unixtime ,
Required: True ,
}
integer ,
prompt_filter_results:
{
Description: Content filtering results for zero or more prompts in the request. In a streaming request, results for different prompts may arrive at different times or in different orders. ,
Required: False ,
}
[
{
prompt_index:
{
Description: The index of this prompt in the set of prompt results ,
Format: int32 ,
Required: True ,
}
integer ,
content_filter_results:
{
Description: Content filtering results for this prompt ,
Required: True ,
}
{
sexual:
{
Description: Describes language related to anatomical organs and genitals, romantic relationships, acts portrayed in erotic or affectionate terms, physical sexual acts, including those portrayed as an assault or a forced sexual violent act against one’s will, prostitution, pornography, and abuse. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
violence:
{
Description: Describes language related to physical actions intended to hurt, injure, damage, or kill someone or something; describes weapons, etc. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
hate:
{
Description: Describes language attacks or uses that include pejorative or discriminatory language with reference to a person or identity group on the basis of certain differentiating attributes of these groups including but not limited to race, ethnicity, nationality, gender identity and expression, sexual orientation, religion, immigration status, ability status, personal appearance, and body size. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
self_harm:
{
Description: Describes language related to physical actions intended to purposely hurt, injure, or damage one’s body, or kill oneself. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
profanity:
{
Description: Describes whether profanity was detected. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
custom_blocklists:
{
Description: Describes detection results against configured custom blocklists. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
details:
{
Description: The collection of detailed blocklist result information. ,
Required: False ,
}
[
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
id:
{
Description: The ID of the custom blocklist evaluated. ,
Required: True ,
}
string ,
}
,
]
,
}
,
error:
{
Description: Describes an error returned if the content filtering system is down or otherwise unable to complete the operation in time. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: True ,
}
string ,
message:
{
Description: A human-readable representation of the error. ,
Required: True ,
}
string ,
target:
{
Description: The target of the error. ,
Required: False ,
}
string ,
details:
{
Description: An array of details about specific errors that led to this reported error. ,
Required: False ,
}
[
string ,
]
,
innererror:
{
Description: An object containing more specific information than the current object about the error. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: False ,
}
string ,
innererror:
{
Required: False ,
}
string ,
}
,
}
,
jailbreak:
{
Description: Whether a jailbreak attempt was detected in the prompt. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
indirect_attack:
{
Description: Whether an indirect attack was detected in the prompt. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
}
,
}
,
]
,
choices:
{
Description: The collection of completions choices associated with this completions response. Generally, `n` choices are generated per provided prompt with a default value of 1. Token limits and other settings may limit the number of choices generated. ,
Required: True ,
}
[
{
text:
{
Description: The generated text for a given completions prompt. ,
Required: True ,
}
string ,
index:
{
Description: The ordered index associated with this completions choice. ,
Format: int32 ,
Required: True ,
}
integer ,
content_filter_results:
{
Description: Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. ,
Required: False ,
}
{
sexual:
{
Description: Describes language related to anatomical organs and genitals, romantic relationships, acts portrayed in erotic or affectionate terms, physical sexual acts, including those portrayed as an assault or a forced sexual violent act against one’s will, prostitution, pornography, and abuse. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
violence:
{
Description: Describes language related to physical actions intended to hurt, injure, damage, or kill someone or something; describes weapons, etc. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
hate:
{
Description: Describes language attacks or uses that include pejorative or discriminatory language with reference to a person or identity group on the basis of certain differentiating attributes of these groups including but not limited to race, ethnicity, nationality, gender identity and expression, sexual orientation, religion, immigration status, ability status, personal appearance, and body size. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
self_harm:
{
Description: Describes language related to physical actions intended to purposely hurt, injure, or damage one’s body, or kill oneself. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
severity:
{
Description: Ratings for the intensity and risk level of filtered content. ,
Enum:
{
safe: Content may be related to violence, self-harm, sexual, or hate categories but the terms are used in general, journalistic, scientific, medical, and similar professional contexts, which are appropriate for most audiences. ,
low: Content that expresses prejudiced, judgmental, or opinionated views, includes offensive use of language, stereotyping, use cases exploring a fictional world (for example, gaming, literature) and depictions at low intensity. ,
medium: Content that uses offensive, insulting, mocking, intimidating, or demeaning language towards specific identity groups, includes depictions of seeking and executing harmful instructions, fantasies, glorification, promotion of harm at medium intensity. ,
high: Content that displays explicit and severe harmful instructions, actions, damage, or abuse; includes endorsement, glorification, or promotion of severe harmful acts, extreme or illegal forms of harm, radicalization, or non-consensual power exchange or abuse. ,
}
,
Required: True ,
}
enum ,
}
,
profanity:
{
Description: Describes whether profanity was detected. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
custom_blocklists:
{
Description: Describes detection results against configured custom blocklists. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
details:
{
Description: The collection of detailed blocklist result information. ,
Required: False ,
}
[
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
id:
{
Description: The ID of the custom blocklist evaluated. ,
Required: True ,
}
string ,
}
,
]
,
}
,
error:
{
Description: Describes an error returned if the content filtering system is down or otherwise unable to complete the operation in time. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: True ,
}
string ,
message:
{
Description: A human-readable representation of the error. ,
Required: True ,
}
string ,
target:
{
Description: The target of the error. ,
Required: False ,
}
string ,
details:
{
Description: An array of details about specific errors that led to this reported error. ,
Required: False ,
}
[
string ,
]
,
innererror:
{
Description: An object containing more specific information than the current object about the error. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: False ,
}
string ,
innererror:
{
Required: False ,
}
string ,
}
,
}
,
protected_material_text:
{
Description: Information about detection of protected text material. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
}
,
protected_material_code:
{
Description: Information about detection of protected code material. ,
Required: False ,
}
{
filtered:
{
Description: A value indicating whether or not the content has been filtered. ,
Required: True ,
}
boolean ,
detected:
{
Description: A value indicating whether detection occurred, irrespective of severity or whether the content was filtered. ,
Required: True ,
}
boolean ,
URL:
{
Description: The internet location associated with the detection. ,
Format: uri ,
Required: False ,
}
string ,
license:
{
Description: The license description associated with the detection. ,
Required: False ,
}
string ,
}
,
}
,
logprobs:
{
Description: The log probabilities model for tokens associated with this completions choice. ,
Required: True ,
}
object ,
finish_reason:
{
Description: Reason for finishing ,
Enum:
{
stop: Completions ended normally and reached its end of token generation. ,
length: Completions exhausted available token limits before generation could complete. ,
content_filter: Completions generated a response that was identified as potentially sensitive per content moderation policies. ,
function_call: Completion ended normally, with the model requesting a function to be called. ,
tool_calls: Completion ended with the model calling a provided tool for output. ,
}
,
Required: True ,
}
enum ,
}
,
]
,
usage:
{
Description: Usage information for tokens processed and generated as part of this completions operation. ,
Required: False ,
}
{
completion_tokens:
{
Description: The number of tokens generated across all completions emissions. ,
Format: int32 ,
Required: True ,
}
integer ,
prompt_tokens:
{
Description: The number of tokens in the provided prompts for the completions request. ,
Format: int32 ,
Required: True ,
}
integer ,
total_tokens:
{
Description: The total number of tokens processed for the completions request and response. ,
Format: int32 ,
Required: True ,
}
integer ,
}
,
}

⚐ Response (default)

{
$headers:
{
x-ms-error-code:
{
Description: String error code indicating what went wrong. ,
}
string ,
}
,
$schema:
{
Description: A response containing error details. ,
}
{
error:
{
Description: The error object. ,
Required: True ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: True ,
}
string ,
message:
{
Description: A human-readable representation of the error. ,
Required: True ,
}
string ,
target:
{
Description: The target of the error. ,
Required: False ,
}
string ,
details:
{
Description: An array of details about specific errors that led to this reported error. ,
Required: False ,
}
[
string ,
]
,
innererror:
{
Description: An object containing more specific information than the current object about the error. ,
Required: False ,
}
{
code:
{
Description: One of a server-defined set of error codes. ,
Required: False ,
}
string ,
innererror:
{
Required: False ,
}
string ,
}
,
}
,
}
,
}