RouterPlus · Schema

GetV1GenerationResponse

AIInferenceLLMRoutingCloudPlatform

Properties

Name Type Description
request_id string Echo of the queried id
admission_events array List of limit or balance refusals recorded before any attempt
attempts array Per‑attempt audit objects
attempts[].attempt number Physical dispatch ordinal, starting at 1
attempts[].deployment string Deployment that served this attempt
attempts[].model string Model id used for the attempt
attempts[].outcome string See outcome table
attempts[].usage_provenance string observed, unknown, or estimated
attempts[].tokens object Token counts for the attempt
attempts[].tokens.input number Input tokens (cache‑inclusive)
attempts[].tokens.cached number Cached reads
attempts[].tokens.cache_write number Cache writes
attempts[].tokens.output number Output tokens (or charge in micro‑dollars)
attempts[].tokens.reasoning number Reasoning tokens (subset of output)
attempts[].reserved_max_usd number Worst‑case hold taken before dispatch
attempts[].cost_usd number Settled cost, includes any web‑search fee
attempts[].billing_source string house or byok
attempts[].inference_cost_usd number Cost attributed from pinned rates
attempts[].inference_price_source string platform_list, customer_rate, unknown, or legacy_platform_list
attempts[].price_snapshot_id string Identifier of the pinned rate snapshot
attempts[].fee_policy_version string Economic policy applied to this attempt
attempts[].error_code string Canonical error class on failure
attempts[].error_origin string Where a failure came from
attempts[].admission_context object Limits claimed at dispatch
attempts[].route_context object Route plan behind this attempt
attempts[].dropped_params array Parameter paths dropped for this deployment
attempts[].dispatched_at string Dispatch timestamp
attempts[].server_tool_use object Web‑search and fetch calls the provider ran
attempts[].server_tool_fee_usd number Part of cost_usd that is web‑search fees
View JSON Schema on GitHub

JSON Schema

routerplus-com-get-v1-generation-response-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/routerplus-com/json-schema/routerplus-com-get-v1-generation-response-schema.json",
  "title": "GetV1GenerationResponse",
  "x-generated": "2026-10-29",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/_ae-authored/routerplus-com-openapi-generated.yml#/components/schemas/GetV1GenerationResponse",
  "type": "object",
  "properties": {
    "request_id": {
      "type": "string",
      "description": "Echo of the queried id"
    },
    "admission_events": {
      "type": "array",
      "description": "List of limit or balance refusals recorded before any attempt"
    },
    "attempts": {
      "type": "array",
      "description": "Per‑attempt audit objects"
    },
    "attempts[].attempt": {
      "type": "number",
      "description": "Physical dispatch ordinal, starting at 1"
    },
    "attempts[].deployment": {
      "type": "string",
      "description": "Deployment that served this attempt"
    },
    "attempts[].model": {
      "type": "string",
      "description": "Model id used for the attempt"
    },
    "attempts[].outcome": {
      "type": "string",
      "description": "See outcome table"
    },
    "attempts[].usage_provenance": {
      "type": "string",
      "description": "observed, unknown, or estimated"
    },
    "attempts[].tokens": {
      "type": "object",
      "description": "Token counts for the attempt"
    },
    "attempts[].tokens.input": {
      "type": "number",
      "description": "Input tokens (cache‑inclusive)"
    },
    "attempts[].tokens.cached": {
      "type": "number",
      "description": "Cached reads"
    },
    "attempts[].tokens.cache_write": {
      "type": "number",
      "description": "Cache writes"
    },
    "attempts[].tokens.output": {
      "type": "number",
      "description": "Output tokens (or charge in micro‑dollars)"
    },
    "attempts[].tokens.reasoning": {
      "type": "number",
      "description": "Reasoning tokens (subset of output)"
    },
    "attempts[].reserved_max_usd": {
      "type": "number",
      "description": "Worst‑case hold taken before dispatch"
    },
    "attempts[].cost_usd": {
      "type": "number",
      "description": "Settled cost, includes any web‑search fee"
    },
    "attempts[].billing_source": {
      "type": "string",
      "description": "house or byok"
    },
    "attempts[].inference_cost_usd": {
      "type": "number",
      "description": "Cost attributed from pinned rates"
    },
    "attempts[].inference_price_source": {
      "type": "string",
      "description": "platform_list, customer_rate, unknown, or legacy_platform_list"
    },
    "attempts[].price_snapshot_id": {
      "type": "string",
      "description": "Identifier of the pinned rate snapshot"
    },
    "attempts[].fee_policy_version": {
      "type": "string",
      "description": "Economic policy applied to this attempt"
    },
    "attempts[].error_code": {
      "type": "string",
      "description": "Canonical error class on failure"
    },
    "attempts[].error_origin": {
      "type": "string",
      "description": "Where a failure came from"
    },
    "attempts[].admission_context": {
      "type": "object",
      "description": "Limits claimed at dispatch"
    },
    "attempts[].route_context": {
      "type": "object",
      "description": "Route plan behind this attempt"
    },
    "attempts[].dropped_params": {
      "type": "array",
      "description": "Parameter paths dropped for this deployment"
    },
    "attempts[].dispatched_at": {
      "type": "string",
      "description": "Dispatch timestamp"
    },
    "attempts[].server_tool_use": {
      "type": "object",
      "description": "Web‑search and fetch calls the provider ran"
    },
    "attempts[].server_tool_fee_usd": {
      "type": "number",
      "description": "Part of cost_usd that is web‑search fees"
    }
  }
}

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/routerplus-com-get-v1-generation-response"
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.