Properties
| Name | Type | Description |
|---|---|---|
| model | string | ID of the model to use for this response. |
| input | object | Text, image, or file inputs to the model. Can be a string or an array of input items. |
| instructions | stringnull | A system (or developer) message inserted into the model's context. |
| stream | booleannull | If true, response data will be streamed as server-sent events. |
| temperature | numbernull | Sampling temperature between 0 and 2. Higher values make output more random. |
| top_p | numbernull | Nucleus sampling: consider tokens with top_p probability mass. Greater than 0 and at most 1. |
| max_output_tokens | integernull | Upper bound for tokens that can be generated, including visible output and reasoning tokens. |
| tools | array | An array of function tools the model may call while generating a response. |
| tool_choice | object | How the model should select which tool to use. "none", "auto", "required", or a specific tool. |
| parallel_tool_calls | booleannull | Whether to allow the model to run tool calls in parallel. |
| reasoning | objectnull | Configuration for reasoning models: effort level and summary format. |
| truncation | stringnull | "auto" truncates input to fit context window. "disabled" (default) returns 400 if input exceeds context. |
| previous_response_id | stringnull | A non-empty value is rejected with 400 unsupported_value: response objects are not stored. Send the earlier turns in `input`. |
| store | booleannull | Accepted for compatibility and ignored. Response objects are not stored. |
| metadata | objectnull | Set of key-value pairs for additional information. |
| text | object | Configuration for text response format (text, json_object, json_schema). |
| top_logprobs | integernull | Number of most likely tokens to return at each position (0-20). |
| seed | integernull | If specified, the system will attempt deterministic sampling. |
| stop | object | Up to 4 sequences where the API will stop generating further tokens. |
| top_k | integernull | Number of highest probability tokens to keep for top-k sampling. -1 to disable. |
| repetition_penalty | numbernull | Penalizes new tokens based on whether they appear in the generated text so far. Values > 1.0 penalize repetitions. |
| min_tokens | integer | Minimum number of tokens to generate before allowing a stop condition. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/aiand-com/json-schema/aiand-com-create-response-request-schema.json",
"title": "CreateResponseRequest",
"x-generated": "2026-11-01",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/aiand-com-openapi.json#/components/schemas/CreateResponseRequest",
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "ID of the model to use for this response."
},
"input": {
"$ref": "#/$defs/ResponseInput",
"description": "Text, image, or file inputs to the model. Can be a string or an array of input items."
},
"instructions": {
"type": [
"string",
"null"
],
"description": "A system (or developer) message inserted into the model's context."
},
"stream": {
"type": [
"boolean",
"null"
],
"default": false,
"description": "If true, response data will be streamed as server-sent events."
},
"temperature": {
"type": [
"number",
"null"
],
"minimum": 0,
"maximum": 2,
"description": "Sampling temperature between 0 and 2. Higher values make output more random."
},
"top_p": {
"type": [
"number",
"null"
],
"exclusiveMinimum": 0,
"maximum": 1,
"description": "Nucleus sampling: consider tokens with top_p probability mass. Greater than 0 and at most 1."
},
"max_output_tokens": {
"type": [
"integer",
"null"
],
"description": "Upper bound for tokens that can be generated, including visible output and reasoning tokens."
},
"tools": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "function"
},
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"parameters": {
"type": "object",
"additionalProperties": true
},
"strict": {
"type": [
"boolean",
"null"
]
}
},
"required": [
"type",
"name"
],
"additionalProperties": true
},
"description": "An array of function tools the model may call while generating a response."
},
"tool_choice": {
"anyOf": [
{
"type": "string",
"enum": [
"none",
"auto",
"required"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "function"
},
"name": {
"type": "string"
}
},
"required": [
"type",
"name"
]
}
],
"description": "How the model should select which tool to use. \"none\", \"auto\", \"required\", or a specific tool."
},
"parallel_tool_calls": {
"type": [
"boolean",
"null"
],
"description": "Whether to allow the model to run tool calls in parallel."
},
"reasoning": {
"type": [
"object",
"null"
],
"properties": {
"effort": {
"type": "string",
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
},
"summary": {
"type": [
"string",
"null"
],
"enum": [
"auto",
"concise",
"detailed",
null
]
}
},
"description": "Configuration for reasoning models: effort level and summary format."
},
"truncation": {
"type": [
"string",
"null"
],
"enum": [
"auto",
"disabled",
null
],
"description": "\"auto\" truncates input to fit context window. \"disabled\" (default) returns 400 if input exceeds context."
},
"previous_response_id": {
"type": [
"string",
"null"
],
"description": "A non-empty value is rejected with 400 unsupported_value: response objects are not stored. Send the earlier turns in `input`."
},
"store": {
"type": [
"boolean",
"null"
],
"description": "Accepted for compatibility and ignored. Response objects are not stored."
},
"metadata": {
"type": [
"object",
"null"
],
"additionalProperties": {
"type": "string"
},
"description": "Set of key-value pairs for additional information."
},
"text": {
"type": "object",
"properties": {
"format": {
"anyOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "text"
}
},
"required": [
"type"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "json_object"
}
},
"required": [
"type"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "json_schema"
},
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"schema": {
"type": "object",
"additionalProperties": true
},
"strict": {
"type": [
"boolean",
"null"
]
}
},
"required": [
"type",
"name"
]
}
]
}
},
"additionalProperties": true,
"description": "Configuration for text response format (text, json_object, json_schema)."
},
"top_logprobs": {
"type": [
"integer",
"null"
],
"minimum": 0,
"maximum": 20,
"description": "Number of most likely tokens to return at each position (0-20)."
},
"seed": {
"type": [
"integer",
"null"
],
"description": "If specified, the system will attempt deterministic sampling."
},
"stop": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 4
},
{
"type": "null"
}
],
"description": "Up to 4 sequences where the API will stop generating further tokens."
},
"top_k": {
"type": [
"integer",
"null"
],
"minimum": -1,
"description": "Number of highest probability tokens to keep for top-k sampling. -1 to disable."
},
"repetition_penalty": {
"type": [
"number",
"null"
],
"description": "Penalizes new tokens based on whether they appear in the generated text so far. Values > 1.0 penalize repetitions."
},
"min_tokens": {
"type": "integer",
"minimum": 0,
"description": "Minimum number of tokens to generate before allowing a stop condition."
}
},
"required": [
"model",
"input"
],
"additionalProperties": true,
"$defs": {
"ResponseInput": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"properties": {
"role": {
"type": "string",
"enum": [
"user",
"assistant",
"developer",
"system"
]
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "input_text"
},
"text": {
"type": "string"
}
},
"required": [
"type",
"text"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "input_image"
},
"image_url": {
"type": "string"
},
"file_id": {
"type": "string"
},
"detail": {
"type": "string",
"enum": [
"auto",
"low",
"high"
]
}
},
"required": [
"type"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "input_file"
},
"file_id": {
"type": "string"
},
"file_data": {
"type": "string"
},
"filename": {
"type": "string"
}
},
"required": [
"type"
]
}
]
},
"minItems": 1
}
]
}
},
"required": [
"role",
"content"
],
"additionalProperties": true
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "function_call"
},
"call_id": {
"type": "string"
},
"name": {
"type": "string"
},
"arguments": {
"type": "string"
}
},
"required": [
"type",
"call_id",
"name",
"arguments"
],
"additionalProperties": true
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "function_call_output"
},
"call_id": {
"type": "string"
},
"output": {
"type": "string"
}
},
"required": [
"type",
"call_id",
"output"
],
"additionalProperties": true
}
]
},
"minItems": 1
}
],
"description": "Text, image, or file inputs to the model. Can be a string (treated as user message) or an array of input items."
}
}
}Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/aiand-com-create-response-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.