Self-hosted · OpenAI-compatible · Offline license
100+ models behind one OpenAI-compatible endpoint. Per-team budgets enforced before tokens burn. Every query auditable. Postgres as source of truth. Your data never leaves your infra.
Per-team budgets enforced pre-request, not after the bill arrives. tiktoken-based prediction refuses calls that would breach budget — before they cost you anything.
✓ team:eng prompt → 1,240 tok ≈ $0.018 allow ✓ team:eng prompt → 8,400 tok ≈ $0.121 allow ✗ team:demo prompt → 420 tok ≈ $0.006 block (over $50/day)
Built as a LiteLLM hook.
Every request logged with team, project, user, model, cost, and latency. Postgres is the single source of truth. Ed25519 offline licensing — no phone-home, no vendor cloud.
Air-gapped deployments supported.
OpenAI, Anthropic, Google, Meta, Mistral, Cohere, xAI, DeepSeek, plus self-hosted via Ollama and vLLM. Routing in Cedar. Fallbacks, caching, A/B splits.
Drop-in replacement for any OpenAI SDK call.
Point your existing OpenAI SDK at Scutum. Get cost tracking, audit, routing, and budgets — without touching your application code.
Scutum
from openai import OpenAI
client = OpenAI(
base_url="https://scutum.your-company.com/v1",
api_key=os.environ["SCUTUM_API_KEY"]
)
response = client.chat.completions.create(
model="claude-sonnet-4",
messages=[{"role": "user", "content": "Hello"}]
)
Same SDK. Same code. Different endpoint. Now every call is logged, budgeted, and routable.
Scutum Research is a Perplexity-style search product running on Scutum gateway. Ask any question and the answer can be an interactive component — calculators, charts, comparison tables — rendered in real React, sandboxed, with sources cited inline. Every query routes through your gateway, every model is swappable, every answer hits your audit log.
Asking Scutum Research for a sprint planner. Sliders update the chart in real time.
Powered by Scutum. Every query is auditable. · Every model is pluggable.
If you're in fintech, healthcare, defense, or any team handling proprietary code or customer data, sending every LLM call through Portkey or Helicone isn't an option. You need the same control plane those products offer — cost governance, audit logs, multi-model routing — but running on infrastructure you control.
Scutum is that control plane. Postgres as the source of truth. Ed25519-signed offline licenses. Air-gapped deployments supported. Same enterprise features as the SaaS alternatives, none of the data exfiltration risk.
Free / Self-host
$0
Pro
$499/mo per deployment
Enterprise
Contact sales
All tiers are self-hosted. Your data never leaves your infrastructure.