Source AvailableSelf-hostedOpenAI-compatibleAir-gapped ready v1.6.2 Enterprise ✦

Model Prism

Multi-tenant LLM gateway with intelligent routing and cost control. Drop-in replacement for the OpenAI API — for your entire organization.

Live Demo View on GitHub Documentation

Everything you need

Model Prism bundles all critical features of a production-ready LLM gateway into a single, easily deployable service.

Intelligent Auto-Routing

Classifier-based routing automatically directs each request to the optimal model — based on complexity, context, and configured cost tiers. Rule sets and fallbacks for maximum control.

Multi-Tenant & RBAC

Full tenant isolation: Every team, every customer gets their own API keys, quotas, and permissions. RBAC at tenant and model level, LDAP/SSO integration.

Real-Time Cost Control

Token-accurate cost tracking per tenant, model, and time period. Budget alerts, automatic throttling on overage, and detailed analytics dashboards.

OpenAI-Compatible API

Drop-in replacement for the OpenAI API — no code changes required. Supports Chat Completions, Embeddings, and Function Calling. Compatible with every OpenAI SDK.

Prompt Logging & Audit Trail

Complete audit log of all LLM requests — prompt, response, model, tokens, cost, and timestamp. Exportable for compliance and debugging.

Air-gapped & Scalable

Fully offline with OFFLINE=true — no outbound connections, no telemetry. Stateless architecture for horizontal scaling, Kubernetes-ready with Helm chart.

Up and running in 5 minutes

Start Model Prism instantly with Docker Compose. No database setup, no complex configuration.


docker pull ghcr.io/ai-ohara-systems/model-prism:latest

# 1. Clone the repository
git clone https://github.com/ai-ohara-systems/model-prism
cd model-prism

# 2. Start
docker compose up -d

# → Setup wizard: http://localhost:3000

# 3. Test — drop-in for OpenAI API
curl http://localhost:3000/api/api/v1/chat/completions \
  -H "Authorization: Bearer omp-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model": "auto", "messages": [{"role": "user", "content": "Hello!"}]}'

# 1. Start MongoDB
docker run -d --name model-prism-mongo \
  -p 27017:27017 \
  -v model-prism-data:/data/db \
  mongo:7

# 2. Start Model Prism
docker run -d --name model-prism \
  -p 3000:3000 \
  -e MONGO_URI=mongodb://host.docker.internal:27017/openmodelprism \
  -e JWT_SECRET=$(openssl rand -hex 32) \
  -e ENCRYPTION_KEY=$(openssl rand -hex 16) \
  ghcr.io/ai-ohara-systems/model-prism:latest

# → Setup wizard: http://localhost:3000

# 1. Add Helm repo
helm repo add ohara https://ai-ohara-systems.github.io/ohara-helm
helm repo update

# 2. Install
helm install model-prism ohara/model-prism \
  --namespace model-prism \
  --create-namespace

# 3. Port-forward to setup wizard
kubectl port-forward svc/model-prism 3000:80 -n model-prism

# → Setup wizard: http://localhost:3000

Full setup guide View on GitHub

Supported Providers

Model Prism connects to all major LLM providers through unified adapters.

OpenAI

Anthropic

Google

Mistral

Cohere

Ollama

+ any OpenAI-compatible endpoint (vLLM, LM Studio, LocalAI, ...)

Ready to deploy Model Prism?

Source Available (ELv2), production-ready. Fully air-gapped with OFFLINE=true — no outbound connections. Enterprise license available for advanced features.

Model Prism on GitHub