Anzoth
Log inGet started
OpenAI-compatible API

Private inference.
Built like a platform.

Your app connects once. handles routing, customer keys, RAG, model access, and governed tools behind a clean OpenAI-compatible API.

✓ Scoped keys✓ Usage tracking✓ RAG support✓ Tool access
emblem
Anzoth API · chat completions
curl https://api.anzoth.com/v1/chat/completions \
-H "Authorization: Bearer anz-••••••••••••" \
-H "Content-Type: application/json" \
-d '{
"model": "Anzoth-Core",
"messages": [{ "role": "user", "content": "Hello" }]
}'
POST /v1/chat/completions200 OK
OpenAI-compatible
drop-in SDK support
Private routing
Anzoth-controlled infra
Scoped keys
per-customer tokens
Usage logs
every request tracked
RAG support
hybrid retrieval

Drop-in compatible

Works with your existing code.

is OpenAI-compatible. Point your SDK at our endpoint, swap your key, and go. No refactoring your request shapes or handling logic.

endpointone-line swap
−api.openai.com/v1
+api.anzoth.com/v1

Compatible clients

Python
openai>=1.0
JavaScript
openai npm
LangChain
ChatOpenAI
curl
any HTTP client
Keep your routing logic, request shapes, and error handling. Only the base URL and API key change.

Platform

Everything between your app and the model.

Gateway

Request routing

Every call passes through our gateway. Authentication, rate limiting, model routing, and usage tracking — handled before your model sees a token.

Keys

Customer API keys

Issue per-customer keys with scoped permissions, token quotas, and RPM limits. Revoke or rotate at any time from your admin panel.

Access

Governed access

Control which models each customer can call. Enable or restrict RAG, tools, and file access per key without touching the model server.

Knowledge bases

Your data. In every answer.

Upload documents, connect a knowledge base, and your model answers with your content — not guesses.

Hybrid retrieval
Dense and sparse vectors combined. Semantic search with keyword fallback.
Customer isolation
Each customer's documents are strictly segmented. No cross-tenant RAG leakage.
Citation tracking
Every answer includes source references so customers can verify accuracy.
Knowledge base
product-docs-v2
Indexed
architecture-overview.pdf
2.1 MB
✓ indexed
api-reference-v3.pdf
890 KB
✓ indexed
changelog-2025.md
44 KB
⟳ processing
3 documents · 14,802 chunks · Last indexed 2h ago

API Keys

One key. Full control.

Issue per-customer keys with scoped permissions, spending limits, per-key rate controls, and last-used tracking.

Scope keys to specific endpoints
Set monthly token and dollar caps
Revoke or rotate at any time
Full per-request audit trail
API Keys
Genesis API Key
Genesis API Key · anz_************************9mP
Last used 4m ago
Active
Scopes:chat:completionsrag:queryfiles:read
Monthly usage1.24M / 5M tokens

Security

Built for private inference.

Client apps connect to our API gateway. The gateway handles authentication, routing, usage tracking, model access, RAG, and tool orchestration. Your traffic is routed through -controlled infrastructure with customer-level access controls.

Key storage
Keys are hashed at write time. The plaintext is shown once, then never stored.
Isolation
Usage data and RAG documents are tenant-scoped. No cross-customer access.
Audit logs
Every request is logged with model, key, latency, tokens, and status code.
Rate limiting
Token and request limits are enforced at the gateway before the model is reached.

Ready to build?

Get an API key and make your first call in minutes.