PostV1ChatCompletionsRequest

AIOpen-SourceFinanceConsultingLaw

Properties

Name	Type	Description
model	string	ultramarine-1-flash
messages	string	Required, non-empty array. Roles: system, user, assistant, tool
reasoning_effort	string	low, high, or max. Default: max
max_completion_tokens	string	Positive integer, including reasoning
stream	string	Boolean. Default: false
stream_options	string	Set {"include_usage": true} to receive stream usage
tools	string	Function tools and tool selection
tool_choice	string	Tool selection
parallel_tool_calls	string	Parallel tool calls
response_format	string	Structured output: json_object or json_schema, or plain text
temperature	string	Number, 0–2. Default and recommended: 1
top_p	string	Number, 0–1. Default and recommended: 0.95
top_k	string	Integer, -1 or greater. Default and recommended: -1
min_p	string	Minimum-probability sampling control
presence_penalty	string	Token selection control
frequency_penalty	string	Token selection control
repetition_penalty	string	Token selection control
logit_bias	string	Token selection control
logprobs	string	Token probabilities
top_logprobs	string	Token probabilities. Must be an integer, 0–20
n	string	Integer, 1–16. Default: 1
stop	string	A string or up to 16 non-empty strings, each at most 1,024 characters
seed	string	Sampling seed
prompt_cache_key	string	Optional cache hint
user	string	User identifier

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/paper-instruments/json-schema/paper-instruments-post-v1-chat-completions-request-schema.json",
  "title": "PostV1ChatCompletionsRequest",
  "x-generated": "2026-10-29",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/_ae-authored/paper-instruments-openapi-generated.yml#/components/schemas/PostV1ChatCompletionsRequest",
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "ultramarine-1-flash"
    },
    "messages": {
      "type": "string",
      "description": "Required, non-empty array. Roles: system, user, assistant, tool"
    },
    "reasoning_effort": {
      "type": "string",
      "description": "low, high, or max. Default: max"
    },
    "max_completion_tokens": {
      "type": "string",
      "description": "Positive integer, including reasoning"
    },
    "stream": {
      "type": "string",
      "description": "Boolean. Default: false"
    },
    "stream_options": {
      "type": "string",
      "description": "Set {\"include_usage\": true} to receive stream usage"
    },
    "tools": {
      "type": "string",
      "description": "Function tools and tool selection"
    },
    "tool_choice": {
      "type": "string",
      "description": "Tool selection"
    },
    "parallel_tool_calls": {
      "type": "string",
      "description": "Parallel tool calls"
    },
    "response_format": {
      "type": "string",
      "description": "Structured output: json_object or json_schema, or plain text"
    },
    "temperature": {
      "type": "string",
      "description": "Number, 0–2. Default and recommended: 1"
    },
    "top_p": {
      "type": "string",
      "description": "Number, 0–1. Default and recommended: 0.95"
    },
    "top_k": {
      "type": "string",
      "description": "Integer, -1 or greater. Default and recommended: -1"
    },
    "min_p": {
      "type": "string",
      "description": "Minimum-probability sampling control"
    },
    "presence_penalty": {
      "type": "string",
      "description": "Token selection control"
    },
    "frequency_penalty": {
      "type": "string",
      "description": "Token selection control"
    },
    "repetition_penalty": {
      "type": "string",
      "description": "Token selection control"
    },
    "logit_bias": {
      "type": "string",
      "description": "Token selection control"
    },
    "logprobs": {
      "type": "string",
      "description": "Token probabilities"
    },
    "top_logprobs": {
      "type": "string",
      "description": "Token probabilities. Must be an integer, 0–20"
    },
    "n": {
      "type": "string",
      "description": "Integer, 1–16. Default: 1"
    },
    "stop": {
      "type": "string",
      "description": "A string or up to 16 non-empty strings, each at most 1,024 characters"
    },
    "seed": {
      "type": "string",
      "description": "Sampling seed"
    },
    "prompt_cache_key": {
      "type": "string",
      "description": "Optional cache hint"
    },
    "user": {
      "type": "string",
      "description": "User identifier"
    }
  },
  "required": [
    "model",
    "messages"
  ]
}

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.

All 92 tools →

Call it yourself

curl for this page

This JSON Schema

curl "https://apis.io/api/v1/json-schemas/paper-instruments-post-v1-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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.