GET

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

kind outputactivity chathash 0e56f09b…extracted Oct 7, 2026version currentsource upstream spec ↗

Response body

33 properties · 8 required · 42 $defs
propertytypedescriptionconstraints
id*stringUnique identifier for this Response.
object*enumThe object type of this resource - always set to `response`.response
created_at*integerUnix timestamp (in seconds) of when this Response was created.format: unixtime
error*OpenAI.ResponseErrorAn error object returned when the model fails to generate a Response.nullable
incomplete_details*OpenAI.ResponseIncompleteDetailsnullable
output*OpenAI.OutputItem[]An array of content items generated by the model. - The length and order of items in the `output` array is dependent on the model's response. - Rather than accessing the first item in the `output` array and assuming it's an `assistant` message with the content…
instructions*string | OpenAI.InputItem[]nullable
parallel_tool_calls*booleanWhether to allow the model to run tool calls in parallel.default: true
metadataOpenAI.MetadataSet 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 characte…nullable
top_logprobsintegernullable
temperaturenumbernullable
top_pnumbernullable
userstringThis field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help…deprecated
safety_identifierstringA stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email…length ≤ 64
prompt_cache_keystringUsed by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching).
prompt_cache_retentionenumin_memory | 24h · nullable
previous_response_idstringnullable
modelstringModel ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](/docs/models) to browse and compare available models.
reasoningOpenAI.Reasoning**gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning).nullable
backgroundbooleannullable
max_tool_callsintegernullable
textOpenAI.ResponseTextParamConfiguration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](/docs/guides/text) - [Structured Outputs](/docs/guides/structured-outputs)
toolsOpenAI.Tool[]An array of tools the model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter. We support the following categories of tools: - **Built-in tools**: Tools that are provided by OpenAI that extend the mo…
tool_choiceenum | object
promptOpenAI.PromptReference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts).
truncationenumauto | disabled · nullable
statusenumThe status of the response generation. One of `completed`, `failed`, `in_progress`, `cancelled`, `queued`, or `incomplete`.completed | failed | in_progress | cancelled | queued | incomplete
completed_atstringformat: date-time · nullable
output_textstringnullable
usageOpenAI.ResponseUsageRepresents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
conversationOpenAI.ConversationReferenceThe conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.nullable
max_output_tokensintegernullable
content_filtersAzureContentFilterForResponsesAPI[]The content filter results from RAI.

Validate a payload

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