FLOATPOINT — SHARED INFERENCE PLATFORM

Every model. Every provider. One platform.

Stop wiring up a dozen providers. Greyroom handles model routing, provider management, and tool execution — so you can just build.

What is Greyroom?

Greyroom is Floatpoint's shared inference platform. Instead of every product wiring up its own connections to a dozen different AI providers, they all go through Greyroom.

It picks the right model and provider for each request, handles the call, and returns a clean, structured response. Services like Observe AMS, CRQ, and everything else we build all run through the same layer.

Greyroom isn't generating AI or making decisions. It's infrastructure that routes inference requests to the best available model and gives you predictable results every time.

greyroom.service
$ greyroom.route("classify")
├─ provider selected anthropic
├─ model claude-sonnet-4-6
├─ tokens 1,247
└─ latency 312ms
response delivered
3+
Providers routed
40+
Models available
312ms
p50 latency
99.9%
Uptime

Core Capabilities

One platform between your products and a growing list of AI providers. Greyroom handles the complexity so your teams don't have to.

01

Smart Routing

Picks the right model and provider for each request based on the task, cost, and latency needs. No hardcoded provider logic in your product code.

02

Unified API

One interface for every provider. Swap models or providers without touching a line of product code.

greyroom.chat({
provider: "anthropic",
task: "classify",
})
03

Tool Execution

Structured tool calling with predictable results. Every invocation gets validated and sandboxed, so products can trust what comes back.

04

Shared Primitives

Common building blocks for classification, extraction, summarization, and scoring. Solved once, reused across every product.

05

Built-in Guardrails

Every request runs through the same safety checks and content policies. No product ships without them.

Usage Tracking 06

See token usage, costs, and latency across every provider and product from one place. No more surprise bills.

Need a primitive we don't have yet?

Talk to us

How it works

Products send inference requests. Greyroom routes each one to the right model and sends back a structured response.

FLOATPOINT PRODUCTS INFERENCE REQUESTS ↓ STRUCTURED RESPONSES ↓ AI PROVIDERS Observe AMS CRQ Future Products Greyroom routing providers execution guardrails OpenAI Anthropic Google + more

Infrastructure, not intelligence. The models do the thinking — Greyroom just makes sure the right one gets the job.

OPEN TO COLLABORATIONS

Build on Greyroom.

Greyroom runs Floatpoint's products in production and doesn't have a public API — but if you want a managed inference layer behind what you're building, we're open to working together.