GET

/v1/schemas/openai/chat/responses%2Fcompact

kind inputactivity chathash 7d400de1…extracted Nov 18, 2026version currentsource upstream spec ↗

Request body

9 properties · 1 required · 190 $defs
propertytypedescriptionconstraints
model*ModelIdsShared | enum | stringModel ID used to generate the response, like `gpt-6-astra`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models) to browse and…nullable
inputstring | InputItem[]Text, image, or file inputs to the model, used to generate a responsenullable
previous_response_idstringThe unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://developers.openai.com/api/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`.nullable
instructionsstringA system (or developer) message inserted into the model's context. When used along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) mess…nullable · deprecated
imageImageOptionsParamRequest level image options.
prompt_cache_keystringA key to use when reading from or writing to the prompt cache.length ≤ 64 · nullable
prompt_cache_retentionenumHow long to retain a prompt cache entry created by this request.in_memory | 24h · nullable · deprecated
prompt_cache_optionsPromptCacheOptionsParamOptions for prompt caching. Supported for `gpt-5.6` and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each request can write up to four b…nullable
service_tierenumSpecifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', the…auto | default | fast | flex | priority · nullable

Validate a payload

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