GET

/v1/schemas/azure/chat/completions?kind=output

Accept:

kind outputactivity chathash 41cb1969…extracted Oct 7, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `9fade08c5d30751828e67fecca63b3800567c802d1d6c4c91bba3d193843f7a8` { "fetchedAt": 1791349936, "extractorVersion": "1", "verifiedAt": null }

Response body

8 properties · 5 required · 15 $defs

property	type	description	constraints
id*	string	A unique identifier for the completion.
choices*	OpenAI.CreateCompletionResponseChoices[]	The list of completion choices the model generated for the input prompt.
created*	integer	The Unix timestamp (in seconds) of when the completion was created.	format: unixtime
model*	string	The model used for completion.
object*	enum	The object type, which is always "text_completion"	text_completion
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	OpenAI.CompletionUsage	Usage statistics for the completion request.
prompt_filter_results	AzureContentFilterResultForPrompt[]

Types

15 $defs

AzureContentFilterBlocklistResultobject

A collection of true/false filtering results for configured custom blocklists.

filtered*	boolean	A value indicating whether any of the detailed blocklists resulted in a filtering action.
details	object[]	The pairs of individual blocklist IDs and whether they resulted in a filtering action.

AzureContentFilterCompletionTextSpanobject

A representation of a span of completion text as used by Azure OpenAI content filter results.

completion_start_offset*	integer	Offset of the UTF32 code point which begins the span.	format: int32
completion_end_offset*	integer	Offset of the first UTF32 code point which is excluded from the span. This field is always equal to completion_start_offset for empty spans. This field is always larger than completion_start_offset for non-empty spans.	format: int32

AzureContentFilterCompletionTextSpanDetectionResultobject

filtered*	boolean	Whether the content detection resulted in a content filtering action.
detected*	boolean	Whether the labeled content category was detected in the content.
details*	AzureContentFilterCompletionTextSpan[]	Detailed information about the detected completion text spans.

AzureContentFilterCustomTopicResultobject

A collection of true/false filtering results for configured custom topics.

filtered*	boolean	A value indicating whether any of the detailed topics resulted in a filtering action.
details	object[]	The pairs of individual topic IDs and whether they are detected.

AzureContentFilterDetectionResultobject

A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.

filtered*	boolean	Whether the content detection resulted in a content filtering action.
detected*	boolean	Whether the labeled content category was detected in the content.

AzureContentFilterPersonallyIdentifiableInformationResultAzureContentFilterDetectionResult

A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.

filtered*	boolean	Whether the content detection resulted in a content filtering action.
detected*	boolean	Whether the labeled content category was detected in the content.

AzureContentFilterResultForChoiceobject

A content filter result for a single response item produced by a generative AI system.

sexual	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.
hate	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.
violence	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.
self_harm	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.
profanity	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.
custom_blocklists	AzureContentFilterBlocklistResult	A collection of true/false filtering results for configured custom blocklists.
custom_topics	AzureContentFilterCustomTopicResult	A collection of true/false filtering results for configured custom topics.
error	object	If present, details about an error that prevented content filtering from completing its evaluation.
protected_material_text	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.
protected_material_code	object	A detection result that describes a match against licensed code or other protected source material.
ungrounded_material	AzureContentFilterCompletionTextSpanDetectionResult
personally_identifiable_information	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.

AzureContentFilterResultForPromptobject

A content filter result associated with a single input prompt item into a generative AI system.

prompt_index	integer	The index of the input prompt associated with the accompanying content filter result categories.	format: int32
content_filter_results	object	The content filter category details for the result.

AzureContentFilterSeverityResultobject

A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.

filtered*	boolean	Whether the content severity resulted in a content filtering action.
severity*	enum	The labeled severity of the content.	safe \| low \| medium \| high

AzurePiiSubCategoryResultobject

Result details for individual PIIHarmSubCategory(s).

sub_category*	string	The PIIHarmSubCategory that was evaluated.
filtered*	boolean	Whether the content detection resulted in a content filtering action for this subcategory.
detected*	boolean	Whether the labeled content subcategory was detected in the content.
redacted*	boolean	Whether the content was redacted for this subcategory.

OpenAI.CompletionUsageobject

Usage statistics for the completion request.

completion_tokens*	integer	Number of tokens in the generated completion.
prompt_tokens*	integer	Number of tokens in the prompt.
total_tokens*	integer	Total number of tokens used in the request (prompt + completion).
completion_tokens_details	OpenAI.CompletionUsageCompletionTokensDetails	Breakdown of tokens used in a completion.
prompt_tokens_details	OpenAI.CompletionUsagePromptTokensDetails	Breakdown of tokens used in the prompt.

OpenAI.CompletionUsageCompletionTokensDetailsobject

accepted_prediction_tokens	integer
audio_tokens	integer
reasoning_tokens	integer
rejected_prediction_tokens	integer

OpenAI.CompletionUsagePromptTokensDetailsobject

audio_tokens	integer
cached_tokens	integer

OpenAI.CreateCompletionResponseChoicesobject

finish_reason*	enum		stop \| length \| content_filter
index*	integer		format: int32
logprobs*	OpenAI.CreateCompletionResponseChoicesLogprobs		nullable
text*	string
content_filter_results	AzureContentFilterResultForChoice	A content filter result for a single response item produced by a generative AI system.

OpenAI.CreateCompletionResponseChoicesLogprobsobject

text_offset	integer[]
token_logprobs	number[]
tokens	string[]
top_logprobs	object[]

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"azure","endpointId":"completions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}