GET

/v1/schemas/meta/chat/v1%2Fresponses?kind=output

kind outputactivity chathash fea31d93…extracted Oct 27, 2026version currentsource upstream spec ↗

Response body

34 properties · 14 required · 98 $defs
propertytypedescriptionconstraints
metadata*objectnullable
temperature*numberWhat 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. (minimum: 0, maximum: 2, default: 1)nullable
top_p*numberNucleus sampling: only tokens whose cumulative probability is at most this value are considered. Must be greater than 0; values <= 0 return HTTP 400. Set this or temperature, not both. (minimum: 0, maximum: 1, default: 1)nullable
model*stringID of the model used to generate the response.
tools*tool[]
tool_choice*tool-choice-param
id*stringIdentifier for this response.
object*enumObject type; always response.response
created_at*numberUnix timestamp (seconds) for when the response was created.
error*objectnullable
incomplete_details*objectExplains why the response is incomplete.nullable
output*output-item[]The items the model generated. Their number and order depend on the response; where SDKs expose it, prefer the output_text helper over indexing into this array.
instructions*string | input-item[]Developer-level instructions inserted at the top of the model's context. When previous_response_id is set, instructions from the prior response are not carried forward, so you can change them on each turn.nullable
parallel_tool_calls*booleanWhether the model may run tool calls in parallel. (default: true)default: true
top_logprobsintegerAn integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. (minimum: 0, maximum: 20)nullable
userstringDeprecated. Being replaced by safety_identifier and prompt_cache_key; use prompt_cache_key to retain caching benefits. A stable end-user identifier used to improve cache hit rates and help detect abuse.
safety_identifierstringA stable identifier that helps detect users who may be violating usage policies. Use a string that uniquely identifies each user, up to 64 characters; hash a username or email so you do not send identifying information. (maxLength: 64)length ≤ 64
prompt_cache_keystringGroups similar requests to improve cache hit rates. Replaces the user field.
service_tierenumauto | default | flex | scale | priority · nullable
prompt_cache_retentionenumThe retention policy for the prompt cache.in_memory | 24h · nullable
previous_response_idstringIdentifier of a previous response to continue from. Use this to build multi-turn conversations with server-managed state. Cannot be combined with conversation.nullable
reasoningreasoningnullable
backgroundbooleanWhether to run the response asynchronously in the background. Cannot be combined with stream. (default: false)nullable
max_tool_callsintegerMaximum number of built-in tool calls allowed while generating a response, counted across all built-in tools rather than per tool. The model ignores any calls beyond this limit. (minimum: 1)nullable
textresponse-text-param
promptobjectnullable
truncationenumTruncation strategy for the request. Only disabled (the default) is supported: if the input plus requested output tokens exceed the model's context window, the request fails with a 400 error. The auto strategy is not supported. (default: disabled)auto | disabled · nullable
statusenumGeneration status: one of completed, failed, in_progress, cancelled, queued, or incomplete.completed | failed | in_progress | cancelled | queued | incomplete
completed_atnumberUnix timestamp (in seconds) when the response completed. Set only when status is completed.nullable
output_textstringSDK-only helper that concatenates the text from all output_text items in output. Available in the Python and JavaScript SDKs.nullable
usageresponse-usage
storebooleanWhether to persist the generated response so it can be retrieved later and chained from previous_response_id. (default: true)nullable
conversationconversation-2(default: null)nullable
max_output_tokensintegerUpper bound on the number of tokens generated for the response, counting both visible output and reasoning tokens.nullable

Validate a payload

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