GET

/v1/schemas/groq/chat/openai%2Fv1%2Fresponses

kind inputactivity chathash 850ec784…extracted Sep 20, 2026version currentsource upstream spec ↗

Request body

17 properties · 2 required · 16 $defs
propertytypedescriptionconstraints
model*string | enumID of the model to use. For details on which models are compatible with the Responses API, see available [models](https://console.groq.com/docs/models)
input*string | ResponseInputItem[]Text input to the model, used to generate a response.
instructionsstringInserts a system (or developer) message as the first item in the model's context.
max_output_tokensintegerAn upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
temperaturenumberControls randomness in the response generation. Range: 0 to 2. Lower values produce more deterministic outputs, higher values increase variety and creativity.0 ≤ n ≤ 2 · default: 1
top_pnumberNucleus sampling parameter that controls the cumulative probability cutoff. Range: 0 to 1. A value of 0.1 restricts sampling to tokens within the top 10% probability mass.0 ≤ n ≤ 1 · default: 1
toolsResponseTool[]List of tools available to the model. Currently supports function definitions only. Maximum of 128 functions.items ≤ 128
tool_choiceenum | objectControls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call …
textobjectResponse format configuration. Supports plain text or structured JSON output.
reasoningobjectConfiguration for reasoning capabilities when using [models that support reasoning](https://console.groq.com/docs/reasoning).
metadataobjectCustom key-value pairs for storing additional information. Maximum of 16 pairs.
parallel_tool_callsbooleanEnable parallel execution of multiple tool calls.default: true
storebooleanResponse storage flag. Note: Currently only supports false or null values.default: false
streambooleanEnable streaming mode to receive response data as server-sent events.default: false
userstringOptional identifier for tracking end-user requests. Useful for usage monitoring and compliance.
service_tierenumSpecifies the latency tier to use for processing the request.auto | default | flex · default: "auto"
truncationenumContext truncation strategy. Supported values: `auto` or `disabled`.auto | disabled · default: "disabled"

Validate a payload

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