Research Project This is a free AI research project. No warranties, SLAs, or company associations. Learn more
Starter
$0
Forever. No credit card.
  • 1,000 requests/day
  • 3 provider keys (BYOK)
  • Thompson Sampling routing
  • Semantic cache (100MB)
  • Guardian Intelligence headers
  • 1 API key
  • Community support
Get Started
Enterprise
$0
Free during research phase
  • Unlimited requests
  • Unlimited provider keys
  • All features included
  • BYOK encryption (KMS)
  • Per-tenant KMS + custom IAM role
  • Prompt rewrite suggestions
  • Dedicated infrastructure
  • Custom guardrail validators
  • Governance & compliance APIs
  • MCP gateway
  • SSO / SAML
  • 99.9% SLA
  • Dedicated support engineer
Contact Sales

Included in every plan

These aren't upsells. They're the foundation.

Zero markup on models

You bring your own API keys. You pay providers directly at their published rates. BrainstormRouter never marks up model costs.

OpenAI compatible

Works with any OpenAI SDK, LangChain, Vercel AI SDK, CrewAI, LlamaIndex. Change your base URL. That's it.

Thompson Sampling

Adaptive routing is available on all plans. The router learns which models work best for your workloads from day one.

Semantic cache

Vector similarity caching is included. Free tier gets 100MB; Pro gets 10GB; Enterprise is unlimited.

Cost visibility

Guardian Intelligence headers ship on every response. You always know what a request cost, which model handled it, and why.

Circuit breakers

Automatic provider failover. If a provider goes down, your requests route to alternatives without code changes.

Questions

Do you mark up model costs?

No. You bring your own API keys and pay providers directly. BrainstormRouter charges for the routing and intelligence layer only.


Can I self-host?

Yes. BrainstormRouter ships as a Docker image and npm package. Self-hosted deployments get all features. Enterprise customers get dedicated infrastructure support.


What counts as a "request"?

One API call to /v1/chat/completions or any other completion endpoint. Cache hits count as requests (but at a lower rate). Memory operations are separate.


What if I exceed my daily limit?

During the research phase, all tiers are free. Limits are soft — if you hit them, reach out and we'll raise them.


Do cache hits reduce my bill?

Yes. Cache hits don't call external providers, so you pay zero model costs. They count as BrainstormRouter requests at a reduced rate. Higher cache hit rates directly reduce your total spend.


Is there a commitment?

No. Everything is free during the research phase. No credit card. No contracts.

Start free

1,000 requests/day. No credit card.

See Thompson Sampling learn your workload. Watch costs drop in the Guardian headers.