Properties
| Name | Type | Description |
|---|---|---|
| model | string | |
| messages | array | |
| max_tokens | integer | |
| max_completion_tokens | object | |
| temperature | number | |
| response_format | object | |
| stop | object | |
| stream | boolean | |
| stream_options | object | |
| task_hint | object | |
| interactive_deadline_ms | object | Optional caller deadline in milliseconds. Basic structured work uses the CPU fast lane; advanced chat uses Qwen3 and returns no_specialists when that lane is unavailable. |
| prefer_async | boolean | |
| prefer_warm | boolean | |
| namespace | object | Private learned-routing namespace used by model='auto'. |
| routing_mode | string | default permits the bounded same-kind fallback; strict requires a live private proof. |
| tools | object | |
| tool_choice | object | Honored end-to-end for unary requests. With stream=true, a demanded named or required choice runs through the same model-backed unary tool contract and its validated result is re-emitted as SSE; no to |
| parallel_tool_calls | object | |
| functions | object | |
| function_call | object | |
| memory | object | |
| automatic_memory | object |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/huggingbay-xyz/json-schema/huggingbay-xyz-chat-completions-request-schema.json",
"title": "ChatCompletionsRequest",
"x-generated": "2026-10-30",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/huggingbay-xyz-run-openapi.json#/components/schemas/ChatCompletionsRequest",
"properties": {
"model": {
"type": "string",
"title": "Model"
},
"messages": {
"items": {
"$ref": "#/$defs/ChatMessage"
},
"type": "array",
"title": "Messages"
},
"max_tokens": {
"type": "integer",
"title": "Max Tokens",
"default": 512
},
"max_completion_tokens": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Max Completion Tokens"
},
"temperature": {
"type": "number",
"title": "Temperature",
"default": 0.0
},
"response_format": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Response Format"
},
"stop": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Stop"
},
"stream": {
"type": "boolean",
"title": "Stream",
"default": false
},
"stream_options": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Stream Options"
},
"task_hint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Task Hint"
},
"interactive_deadline_ms": {
"anyOf": [
{
"type": "integer",
"maximum": 120000.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Interactive Deadline Ms",
"description": "Optional caller deadline in milliseconds. Basic structured work uses the CPU fast lane; advanced chat uses Qwen3 and returns no_specialists when that lane is unavailable."
},
"prefer_async": {
"type": "boolean",
"title": "Prefer Async",
"default": false
},
"prefer_warm": {
"type": "boolean",
"title": "Prefer Warm",
"default": true
},
"namespace": {
"anyOf": [
{
"type": "string",
"maxLength": 256
},
{
"type": "null"
}
],
"title": "Namespace",
"description": "Private learned-routing namespace used by model='auto'."
},
"routing_mode": {
"type": "string",
"enum": [
"default",
"strict"
],
"title": "Routing Mode",
"description": "default permits the bounded same-kind fallback; strict requires a live private proof.",
"default": "default"
},
"tools": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/ChatFunctionTool"
},
"type": "array",
"maxItems": 128,
"minItems": 1
},
{
"type": "null"
}
],
"title": "Tools"
},
"tool_choice": {
"anyOf": [
{
"type": "string",
"enum": [
"none",
"auto",
"required"
]
},
{
"$ref": "#/$defs/ChatNamedToolChoice"
},
{
"type": "null"
}
],
"title": "Tool Choice",
"description": "Honored end-to-end for unary requests. With stream=true, a demanded named or required choice runs through the same model-backed unary tool contract and its validated result is re-emitted as SSE; no tool-call chunk is emitted unless the model produced that call. Missing or invalid demanded calls fail with a typed non-2xx response before SSE starts. Undemanded tools are ignored while ordinary assistant text streams, declared by x-bay-run-tools-ignored."
},
"parallel_tool_calls": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Parallel Tool Calls"
},
"functions": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/ChatFunctionDefinition"
},
"type": "array",
"maxItems": 128,
"minItems": 1
},
{
"type": "null"
}
],
"title": "Functions"
},
"function_call": {
"anyOf": [
{
"type": "string",
"enum": [
"none",
"auto"
]
},
{
"$ref": "#/$defs/ChatNamedFunctionChoice"
},
{
"type": "null"
}
],
"title": "Function Call"
},
"memory": {
"anyOf": [
{
"$ref": "#/$defs/MemoryInjectionOptions"
},
{
"type": "null"
}
]
},
"automatic_memory": {
"anyOf": [
{
"$ref": "#/$defs/MemoryAutomaticOptions"
},
{
"type": "null"
}
]
}
},
"type": "object",
"required": [
"model",
"messages"
],
"$defs": {
"ChatFunctionDefinition": {
"properties": {
"name": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"pattern": "^[A-Za-z0-9_-]+$",
"title": "Name"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Description"
},
"parameters": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Parameters"
},
"strict": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Strict"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"name"
],
"title": "ChatFunctionDefinition"
},
"ChatFunctionTool": {
"properties": {
"type": {
"type": "string",
"const": "function",
"title": "Type"
},
"function": {
"$ref": "#/$defs/ChatFunctionDefinition"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"type",
"function"
],
"title": "ChatFunctionTool"
},
"ChatMessage": {
"properties": {
"role": {
"type": "string",
"title": "Role"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Content"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name"
},
"tool_call_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Tool Call Id"
},
"tool_calls": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/ChatMessageToolCall"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Tool Calls"
},
"function_call": {
"anyOf": [
{
"$ref": "#/$defs/ChatMessageFunctionCall"
},
{
"type": "null"
}
]
}
},
"type": "object",
"required": [
"role"
],
"title": "ChatMessage"
},
"ChatMessageFunctionCall": {
"properties": {
"name": {
"type": "string",
"title": "Name"
},
"arguments": {
"type": "string",
"title": "Arguments"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"name",
"arguments"
],
"title": "ChatMessageFunctionCall"
},
"ChatMessageToolCall": {
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"type": {
"type": "string",
"const": "function",
"title": "Type"
},
"function": {
"$ref": "#/$defs/ChatMessageFunctionCall"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"id",
"type",
"function"
],
"title": "ChatMessageToolCall"
},
"ChatNamedFunctionChoice": {
"properties": {
"name": {
"type": "string",
"maxLength": 64,
"minLength": 1,
"pattern": "^[A-Za-z0-9_-]+$",
"title": "Name"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"name"
],
"title": "ChatNamedFunctionChoice"
},
"ChatNamedToolChoice": {
"properties": {
"type": {
"type": "string",
"const": "function",
"title": "Type"
},
"function": {
"$ref": "#/$defs/ChatNamedFunctionChoice"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"type",
"function"
],
"title": "ChatNamedToolChoice"
},
"MemoryAutomaticOptions": {
"properties": {
"namespace": {
"type": "string",
"maxLength": 256,
"minLength": 1,
"title": "Namespace",
"default": "default"
},
"key": {
"anyOf": [
{
"type": "string",
"maxLength": 512,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Key"
},
"ttl": {
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0.0
},
{
"type": "null"
}
],
"title": "Ttl",
"description": "Expiry in seconds. Null uses the server's bounded automatic-memory default; automatic memory cannot create an indefinite entry.",
"default": 2592000
},
"importance": {
"type": "integer",
"maximum": 100.0,
"minimum": 0.0,
"title": "Importance",
"default": 0
},
"max_bytes": {
"type": "integer",
"maximum": 16384.0,
"minimum": 256.0,
"title": "Max Bytes",
"default": 16384
},
"semantic": {
"type": "boolean",
"title": "Semantic",
"default": true
}
},
"additionalProperties": false,
"type": "object",
"title": "MemoryAutomaticOptions",
"description": "Opt-in bounded storage policy for a supported inference result."
},
"MemoryInjectionOptions": {
"properties": {
"namespace": {
"type": "string",
"maxLength": 256,
"minLength": 1,
"title": "Namespace",
"default": "default"
},
"query": {
"anyOf": [
{
"type": "string",
"maxLength": 256,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Query"
},
"max_items": {
"type": "integer",
"maximum": 50.0,
"minimum": 1.0,
"title": "Max Items",
"default": 8
},
"max_bytes": {
"type": "integer",
"maximum": 1048576.0,
"minimum": 69632.0,
"title": "Max Bytes",
"default": 69632
},
"max_tokens": {
"type": "integer",
"maximum": 4096.0,
"minimum": 1.0,
"title": "Max Tokens",
"description": "Conservative UTF-8-byte token-equivalent cap for injected memory.",
"default": 4096
}
},
"additionalProperties": false,
"type": "object",
"title": "MemoryInjectionOptions",
"description": "Opt-in, bounded memory retrieval for supported inference tools."
}
}
}
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/huggingbay-xyz-chat-completions-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.