BrainstormRouter Intelligence API

The intelligence API from BrainstormRouter — 38 operation(s) for intelligence.

Operations 42

GET /auth/ops/guardian-stats Guardian overhead, cache hit rate, anomaly count — dashboard JWT #
GET /auth/routing/cascades Cascade activations (model escalation on failure) — dashboard JWT #
GET /auth/routing/decisions Recent routing decisions with decisionTrace metadata (dashboard JWT) #
GET /v1/agent/reputation Caller's own agent reputation: score, tier, and tier multipliers #
GET /v1/agent/trajectories Query stored trajectories with filters (project, request_type, source, limit… #
POST /v1/agent/trajectories Record an orchestration trajectory for the current tenant #
GET /v1/agent/trajectories/export Export trajectories as JSONL for offline training pipelines #
GET /v1/agent/trajectories/stats Aggregate statistics over stored trajectories for the current tenant #
POST /v1/compare Fan a prompt out to 2–6 models in parallel and compare cost/latency/quality #
POST /v1/consensus Evaluate multi-model consensus (majority/quality/weighted) with optional fan-out #
POST /v1/estimate Predict per-model cost for a completion request (no provider calls) #
GET /v1/experiments List experiments for the tenant #
POST /v1/experiments Create an A/B-test experiment with weighted variants #
GET /v1/experiments/{id} Get an experiment with interim results + statistical significance #
POST /v1/experiments/{id}/outcomes Record an outcome for an experiment variant #
GET /v1/explain/{request_id} Per-request routing-decision trace; optional LLM-narrated postmortem #
POST /v1/feedback/{requestId} Report outcome (success/partial/failure) for a routed request; the reward… #
GET /v1/fleet/insights Fleet model insights — top 10 by evaluations or model-specific #
POST /v1/intelligence/advise Predictive routing recommendation with reasoning, evidence, and alternatives #
GET /v1/intelligence/benchmark Thompson-vs-static shadow comparator results + statistical significance #
GET /v1/intelligence/compare Head-to-head comparison of 2-10 models #
GET /v1/intelligence/degradation Current degradation ladder state: level, reason, thresholds, budget utilization #
GET /v1/intelligence/deprecations Active deprecation alerts (filter by provider, level) #
GET /v1/intelligence/frontier Cost-quality Pareto frontier with dominated models #
GET /v1/intelligence/model/{provider}/{modelId} Single model profile with ranking + deprecation alert #
GET /v1/intelligence/patterns Aggregated request-pattern × model performance data with optional filters #
GET /v1/intelligence/rankings Overall (or task-specific) model leaderboard #
GET /v1/intelligence/savings Counterfactual ROI savings (Postgres-backed when configured) #
GET /v1/intelligence/status Ingestor diagnostics, store size, deprecation alert count #
GET /v1/liaison/{liaison_id}/events SSE stream of routing decisions and trace envelopes scoped to a liaison session #
GET /v1/ops/guardian-stats Guardian overhead, cache hit rate, anomaly count (24h) #
POST /v1/patterns Store a learned task pattern (tenant-scoped) #
GET /v1/patterns/recommend Aggregated task-pattern recommendations across all tenants #
POST /v1/recommend Ranked model recommendations backed by production routing data #
POST /v1/route Brainstorm CLI delegated routing — pick a model for a task spec #
GET /v1/routing-stream SSE stream of live routing events for the tenant: route-time decisions… #
DELETE /v1/routing/canary Remove canary configuration #
GET /v1/routing/canary Read current canary configuration #
POST /v1/routing/canary Set the canary traffic-split configuration for the current tenant #
GET /v1/routing/canary/results Per-variant outcome statistics for the active canary #
GET /v1/routing/cascades Cascade activations (model escalation on failure) #
GET /v1/routing/decisions Recent routing decisions with decisionTrace metadata #

Work with this as data

Every API 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 apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • 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 API
curl "https://apis.io/api/v1/apis/brainstormrouter-com:brainstormrouter-com-intelligence-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

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.

OpenAPI Specification

brainstormrouter-com-intelligence-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: BrainstormRouter Intelligence API
  version: 1.0.0
  description: 'Autonomous AI API Engine — multi-tenant gateway that intelligently routes

    AI traffic across providers with built-in memory, cost optimization, and

    autonomous background processing.


    All `/v1/*` endpoints require an API key via `Authorization: Bearer `.'
  contact:
    name: BrainstormRouter
    url: https://brainstormrouter.com
  license:
    name: Proprietary
    identifier: LicenseRef-Proprietary
servers:
- url: https://api.brainstormrouter.com
  description: Production
security:
- BearerAuth: []
tags:


# --- truncated at 32 KB (45 KB total) ---
# Full source: https://artifacts.apis.io/brainstormrouter-com/openapi/brainstormrouter-com-intelligence-api-openapi.yml