One APIfor AI.
CompanyFabric is developer infrastructure: a routing and metering layer that forwards your API requests to third-party model providers under a single key and one balance. Built for developers and businesses integrating AI into their own products. OpenAI-compatible, change one base URL and keep your code.
Compatible with
Price first.
Then generate.
The exact cost sits next to the button and recomputes as you change parameters, before you press it. Free starter credits on signup.
Every major model.
One key.
The fabric routes each request to the best provider, or the exact model you name. Smart modes: companyfabric/auto · fast · cheap · best · code
Text
Frontier chat and reasoning models behind the same OpenAI-compatible endpoint.
$0.075/Mtok in · GLM-5.3-Flash
Code
Point Claude Code or Cursor at one base URL and swap code models per task.
$3/Mtok in · Kimi K3
See what
you get.
Compare models in one chat, watch spend land per request, bring your own keys at 0%, and top up one balance that covers everything.
Chat: compare models side by side
The same prompt to two models at once, each answer priced to the fraction of a cent.
Usage: every request attributed
Daily spend and requests, broken down per model and per key. No invoice archaeology.
BYOK vault: your keys, 0% on top
Bring provider keys and pay nothing extra. Keys are stored encrypted and never logged.
Billing: one balance for everything
Prepaid credits that never expire, plans with a monthly allowance, exact metering underneath.
Three doors.
One balance.
Credits
Prepay once, spend across every model. Exact metering, no subscription required.
BYOK at 0%
Bring your own provider keys and pay nothing on top. Routing and one-key ergonomics stay.
Drop-in compatible
Point any OpenAI SDK at our base URL. Same request shape, same response shape, change two lines, keep your code.
Let your agent
handle it.
Add the MCP server to Claude Code, then just ask: “refactor this module, cheapest model that can do it”. Your agent checks prices, picks the model, runs it, and reports what it cost.
Install for agents# give your agent the catalog
claude mcp add --transport http companyfabric \
https://companyfabric.com/api/mcp \
--header "Authorization: Bearer sk-cf-…"
# or, no install at all
curl companyfabric.com/install.txt
Already
compatible.
Keep your OpenAI SDK. Change the base URL. Every model above is now yours, with exact metered cost on every response.
import OpenAI from "openai"
const client = new OpenAI({
baseURL: "https://api.companyfabric.com/v1",
apiKey: process.env.COMPANYFABRIC_API_KEY,
})
const res = await client.chat.completions.create({
model: "companyfabric/auto",
max_tokens: 1024,
temperature: 0.7,
messages: [{ role: "user", content: "Say hello from the fabric." }],
})
console.log(res.choices[0].message.content)OpenAI-compatible
Existing SDKs and harnesses work unchanged.
Streaming
SSE with a final usage chunk carrying exact cost.
Exact metering
Every response reports what the ledger recorded.
Structured errors
Every error states its machine-actionable fix.
A flat monthly bill.
One price, a monthly usage allowance, every model behind one key. No metering anxiety.
Prefer pay-as-you-go? Bring your own provider keys at 0%, or top up credits. See all pricing →
Every model.
One key.
Free starter credits on signup, enough to try any model in the playground before you spend a cent.