Is Anoman a drop-in replacement for OpenAI?

Yes. Anoman exposes a fully OpenAI-compatible API — point your base_url at Anoman and nothing else changes. Any SDK that works with OpenAI (Python, TypeScript, Go, and others) works with Anoman out of the box.

How does Anoman stop prompt-injection attacks?

Every request passes an ML classifier trained for prompt-injection detection (configurable threshold) plus heuristic and content-moderation checks, blocking malicious prompts before they ever reach a model. Injection detection is mandatory — only the sensitivity is adjustable, never the check itself.

Is my data safe from Anoman itself?

Your prompts and completions are never used to train any model. Cache is partitioned per customer so no one sees another customer's data, API keys are bcrypt-hashed, and PII is detected and masked on every request before it reaches any model.

Where does my data actually go?

It's processed and stored in your configured region. Indonesian data stays in Jakarta and only crosses a border if a specific model you choose declares it — and that's shown on the model's detail page. No silent cross-border transfers.

Is there any lock-in?

No. Anoman is OpenAI-compatible — you changed two lines of config to come in, and you can change them back to leave. There's no proprietary SDK to rip out. Start free, cancel anytime.

Why trust a newer, Indonesia-based vendor?

Because trust here is instrumented, not asserted: every response returns a verifiable receipt of exactly what we did (region, guardrail results, routing, cost), we run a public status page and the Founding 50 program, and Anoman is built by security experts with more than 15 years in enterprise cybersecurity.

Do you have SOC 2 or ISO 27001?

Formal certification is planned. In the meantime we handle enterprise security reviews and vendor questionnaires directly, and every call already returns machine-readable evidence of the controls applied — contact us for provider documentation and a Data Processing Agreement.

What's your uptime and SLA?

We target 99.9% monthly on the gateway and publish live status at anoman.io/status. A contractual SLA is available on the Enterprise plan.

Why not just use LiteLLM or build this myself?

You could — and then you'd own building and maintaining guardrails, PII masking, data residency, batch routing, observability, and audit logging yourself, forever. Anoman ships all of them on every call, maintained, behind one OpenAI-compatible endpoint.

The guarded LLM gateway

Grow your business with AI you can trust.

The guarded AI platform behind your business — 100+ models through one endpoint, with prompt-injection defense, PII masking, and predictable pricing on every call.

# drop-in — change two lines
base_url="https://api.anoman.io/v1"
api_key="anm-sk-…" # guarded · logged · sovereign

Start free Read the docs

injection passPII PII masked 3region IDpolicy pass

300+

models · 10+ providers

<30ms

added latency p50

token markup

🇮🇩 ID

UU PDP residency

Founding 50 · limited seats0% token markup99.9% uptime targetFaithfulness AUC 0.97 EN / 0.999 IDReceipts on every call

464

AI calls guarded

injections blocked

PII entities masked

See the live Trust Summary

Shipping AI is easy. Proving it's safe is the part that stalls deals.

A customer sends a security questionnaire — and you don't have an answer. The deal waits.
One prompt injection or a leaked NIK/email, and it's your name on the breach — with a 72-hour UU PDP clock and up to 2% of revenue on the line.
Your data leaves the country the moment you call a foreign model. No residency, no audit trail, no proof.
Five provider SDKs, rising token bills, and you still can't see what happened on any single call.

Anoman closes all four — on every call.

One key · 100+ models

OpenAIAnthropicGoogleMistralDeepSeekGroqLlamaQwen

Transparency

Security you can read on every call.

Most gateways won't tell you what they did to your request. Anoman returns the receipt — on every single response.

✓Injection score + PII entities masked, per call
✓The exact region your data was processed in
✓An append-only audit trail — the evidence UU PDP asks for

POST /v1/chat/completions200 · 412 ms

X-Anoman-Guardrail-Injectionpass · 0.12

X-Anoman-Guardrail-Piimasked · 3 entities

X-Anoman-Guardrail-Contentpass

X-Anoman-RegionID · Jakarta

X-Anoman-Cachesemantic · hit

Receipts on every call — the audit trail UU PDP asks for, built in.

What Anoman does

Defense-in-depth for every AI call

Guardrails

ML-based prompt-injection detection, PII masking (7 entity types, 4 modes), content moderation in EN + Bahasa Indonesia, conversational flows.

Smart Routing

Latency-based provider selection, batch routing with 50% cost savings on non-interactive workloads, semantic cache, provider-side prompt cache injection.

Full Observability

Every call traced — prompt, completion, cost, latency, guardrail results, routing mode, cache hit. Self-hosted tracing + analytics backend. Real-time SSE live feed.

Policy Control

Tool call allowlist/denylist via AgentPolicy, per-API-key guardrail overrides, MCP server governance with per-tool RBAC and rate limits.

Cost Transparency

0% markup — pay what providers charge. Weighted token formula surfaced per request. Batch savings and cache savings tracked in dashboard.

SEA Compliance

Data residency enforced per API key. Indonesia data center (Jakarta) for UU PDP compliance. IDR billing. Bahasa Indonesia content moderation. Append-only audit log.

Free tools · no signup

Try Anoman's AI safety in your browser

The same protections that run on every Anoman API call — check any prompt or answer right now.

Free · 2 min

Is your AI leaking customer data?

A guided diagnostic for AI builders & founders. Answer a few questions and get a personalized report of your top 5 data-security & UU PDP gaps — generated by AI, sent to your inbox.

AI-generated top-5 gap report
UU PDP & data-residency risk check
Practical fixes you can start this week
Bonus: a customer-trust one-pager template

Run the free diagnostic

No credit card. Just your email for the report.

Run a live guarded call

Live

Run a real LLM call through the full guarded gateway — see prompt injection blocked, PII masked, the cost in Rupiah, and Jakarta residency. No signup.

A real completion on a free model
Prompt injection blocked before the model
Cost in Rupiah · processed in Jakarta

Try a live call free

Guardrails

Catch prompt injection, jailbreaks, PII, and unsafe content in any prompt or response — the same checks that guard every Anoman API call.

Prompt-injection & jailbreak detection
PII detection & masking (incl. SG NRIC / ID NIK)
Content moderation — English + Bahasa

Test guardrails free

Response Faithfulness

New

Does an AI answer actually follow from its source? Detect hallucinations and ungrounded claims in any model's output, with a clear Grounded / Uncertain / Ungrounded verdict.

Groundedness & hallucination detection
Multilingual — English + Bahasa Indonesia
Calibrated accuracy: AUC 0.97 (EN) / 0.999 (ID)

Test faithfulness free

Two ways to use Anoman

Build on the API, or just start chatting

The same guarded, Jakarta-resident engine — whether your developers call it over an API or your team chats in a branded app.

Anoman Gateway

One OpenAI-compatible API to hundreds of models — with guardrails, routing, caching, and full observability. For developers and agents.

Drop-in OpenAI / Anthropic base URL
Prompt-injection + PII guardrails on every call
Batch routing + prompt caching to cut cost

Get API Key Explore the platform →

Anoman Copilot

New

A branded AI chat app for your whole team — the ChatGPT experience, Jakarta-resident and UU-PDP-ready. No code required.

Chat with hundreds of models — vision + streaming
Bahasa PII-masking + per-member model & quota controls
Give non-technical staff safe AI, centrally governed

Open Copilot Learn more →

Request pipeline

How every request flows

Your app calls Anoman

Drop-in replacement for OpenAI or Anthropic SDK. Change base_url and api_key — nothing else.

Guardrails run first

Injection detection, PII masking, content moderation, and a tool-call policy check before any LLM call.

Smart routing decides

Cache hit? Return immediately. Batch-eligible? Enqueue with 50% savings. Otherwise route to the best live provider.

Response + _anoman metadata

Full OpenAI-compatible response plus guardrail results, routing mode, cost, and cache status in _anoman block.

Kedaulatan digital · sampai ke tiap panggilan AI

Your data doesn't leave home to use AI.Kedaulatan digital, sampai ke tiap panggilan AI.

100+ models, guarded and routed in Jakarta. Every AI call masked, logged, and kept under UU PDP — the sovereignty no foreign gateway can offer.

Amankan tiap panggilan AI

1.379

laporan penipuan AI · OJK 2026

72 jam

notifikasi wajib · UU PDP

sanksi pendapatan tahunan

Find your path

Built for your situation

Pick the page that sounds like you — each one has the pains, proof, and answers for that exact situation.

For startups

A customer's asking about your data handling. Ship AI you can prove is safe — start free.

Explore

For compliance

Make your AI stack UU PDP-ready: residency, PII masking, and evidence on every call.

Explore

For Southeast Asia

Rupiah billing, Bahasa-aware guardrails, and data that stays in Jakarta.

Explore

For enterprise

SSO, audit export, residency, and an SLA — pass the security review with evidence.

Explore

Pricing

0% markup. Pay what providers charge.

1 USD = Rp 18,500 · IDR prices rounded for clarity

Pay-As-You-Go

$18/mo + raw cost$9/mo + raw cost

Rp 318rb50% OFF

Rp 159rb

60 RPM200K TPM

All 400+ LLMs
0% base markup
Full guardrails
PAYG billing

Start Free

Starter

$24/mo$12/mo

Rp 418rb50% OFF

Rp 209rb

30 RPM60K TPM

Budget-tier models
Full guardrails
1 API key
IDR billing

Get Started

Refer a friend — you both get 20% credit

When someone you invite subscribes, you each get 20% of their payment back as Anoman credit — on their first 3 settled payments. Credit is spendable on Anoman usage and overage. Grab your invite link from your dashboard.

Get your invite link

Frequently Asked Questions

Everything you need to know about Anoman AI and LLM gateway security.

An LLM gateway is a proxy between your application and the upstream model providers. It routes requests, enforces security policies, meters usage, and gives you observability — through one OpenAI-compatible endpoint. Anoman is the guarded LLM gateway: prompt-injection defense, PII masking, and policy control run on every call.

Start securing your AI calls today.

Free API key. No credit card required. Indonesia and Singapore data residency.

Get API Key Read Docs