For Builders · AI Gateway

OmniStrat Foundry.

One endpoint, every model. Every call cryptographically signed. Cost caps that stop, not warn. Failover fast enough it never wakes you. Taskforces that hold a charter, a budget, and a memory.

This month

Your usage · live
AI calls
Signed by Ed25519
Tokens routed
Across 13 providers
Est. cost
Under your cap
Taskforces
Charter · budget · memory

Console

Manage your Foundry
API Keys

Generate, rotate, revoke.

Long-lived keys or short-lived JWTs. Rotate any time; existing traffic keeps flowing until you revoke.

Taskforces

Build agents that hold charter.

Each Taskforce has a charter, budget, memory that compounds, and an approval workflow you configure per action class.

Cost governance

Hard caps, per-org · per-key · per-call.

Set a monthly ceiling. The Router refuses the 601st dollar. No overages. No surprises. Anomaly detection with drift alerts.

Audit chain

Every call receipted.

Every request, signed. Every response, hash-chained. Publicly verifiable. Compliance ships with the product, not bolted on top.

Quickstart

One line to your first call
POST https://api.omnistrat.ai/api/route
# Bash
curl -X POST https://api.omnistrat.ai/api/route \
  -H "Authorization: Bearer ost_..." \
  -H "X-Org-Id: org_..." \
  -H "Content-Type: application/json" \
  -d '{ "prompt": "Hello", "model": "auto" }'

# TypeScript SDK
npm install @omnistrat/sdk

import { OmniStrat } from "@omnistrat/sdk";
const client = new OmniStrat({ apiKey, orgId });
const r = await client.route({ prompt: "Hello" });

Providers behind the endpoint

13 available · auto-failover
Anthropic
Claude Opus · Sonnet
OpenAI
GPT-5 · GPT-4o
Google
Gemini 2.5 · 1.5
xAI
Grok 4 · 3
Workers AI
Llama · Mistral
Bedrock
via AWS
DeepSeek
R1 · V3
Qwen
Alibaba
Mistral
La Plateforme
Cohere
Command R
Perplexity
Sonar
Groq
Fast inference
Together
OSS models