Everything You Need to Govern AI at Scale
From quickstart to enterprise compliance. Full-featured gateway with governance layers that grow with your requirements.
Drop-in OpenAI-compatible endpoint. Route to OpenAI, Anthropic, Gemini, Azure, Bedrock, or Ollama with zero code changes. Streaming, structured outputs, and vision built-in.
YAML DSL for model allowlists, token limits, MCP tool restrictions, budget-based model downgrades, and time-of-day rules. Dry-run against historical traffic before activation.
HMAC-SHA256 signed, append-only audit records. PostgreSQL RLS prevents tampering. SOC2, HIPAA, and GDPR evidence packages generated on demand.
Separately deployed MCP Proxy governs every tool call. PII scanning on arguments and responses. Human approval gates for high-risk operations. Credential centralisation.
Real-time per-request cost calculation. Budget caps per tenant, team, or API key. Automatic model downgrade at soft limit. Chargeback reports and cost forecasting.
Detect and redact emails, phone numbers, SSNs, credit cards, and custom patterns before they reach any provider. Configurable per-tenant: block, redact, or flag.
Round-robin, weighted, capability-aware, latency-aware, and cost-aware routing. Circuit breakers, failover, and retry with exponential backoff. Canary and A/B testing.
Prometheus metrics, OpenTelemetry distributed tracing, structured JSON logging. Pre-built Grafana dashboards. Unified traces spanning LLM turns and MCP tool calls.
Agent loop detection with auto-kill. Session tracking across LLM and MCP calls. Human-in-the-loop approval gates enforced at execution. Full session timeline and analytics.
Two Governed Data Planes. One Control Plane.
The LLM Gateway sits at the edge for model traffic. The MCP Proxy sits inside your perimeter for tool calls. Both share the same policies, audit trail, and API keys.
Built for Production Scale
Governance with zero performance tax. Every layer is optimised for throughput — lightweight concurrency, non-blocking audit, multi-layer caching, and zero-copy streaming.
Governance Is the Architecture, Not a Feature
In every competitor, governance is bolted onto a proxy. In DVARA, governance is the design constraint that shaped every layer.
Full YAML DSL with version control, conflict detection at load time, and dry-run mode that tests against real historical traffic. Your auditors get proof that policies were tested before deployment.
Every record HMAC-SHA256 signed at write. PostgreSQL RLS blocks UPDATE/DELETE. Chronicle Queue writes < 1 microsecond with zero GC pressure. Tamper-evident by design.
Separately deployed, centrally governed MCP Proxy. Every tool call audited, policy-checked, and PII-scanned. Credential centralisation. Human approval gates enforced at execution.
Full OpenTelemetry trace spanning LLM turns + MCP calls. Agent loop detection with auto-kill. Human-in-the-loop approval for high-risk tool calls. Session-level cost and compliance summary.
Audit-Ready from Day One
Generate compliance evidence packages on demand. Every request is immutably logged, every policy decision recorded, every PII event tracked.
How DVARA Compares
The structural gaps in every competitor are not feature gaps — they require architectural redesigns to close.
| DVARA | LiteLLM | Portkey | Kong AI | Cloudflare | Helicone | AWS Bedrock | Bifrost | |
|---|---|---|---|---|---|---|---|---|
| Core Gateway | ||||||||
| OpenAI-compatible unified API | ✓ | ✓ | ✓ | ∼ | ✓ | — | — | ✓ |
| SSE streaming (zero-copy pass-through) | ✓ | ✓ | ✓ | ✓ | ✓ | — | ✓ | ✓ |
| Structured outputs on Anthropic + Gemini | ✓ | — | — | — | — | — | — | — |
| Multi-provider (OpenAI, Anthropic, Gemini, Bedrock, Azure, Ollama) | ✓ | ✓ | ✓ | ∼ | ∼ | ✓ | ∼ | ✓ |
| Virtual thread concurrency (10K+ RPS) | ✓ | ∼ | ∼ | ✓ | ✓ | — | ✓ | ∼ |
| Routing & Resilience | ||||||||
| Weighted routing + failover | ✓ | ✓ | ✓ | ✓ | ∼ | — | — | ✓ |
| Latency-aware routing (EWMA P95) | ✓ | ∼ | ∼ | — | — | — | — | ∼ |
| Cost-aware routing | ✓ | — | ∼ | — | — | — | — | — |
| Canary + A/B routing | ✓ | — | ∼ | — | — | — | — | — |
| Per-provider circuit breaker | ✓ | ∼ | ∼ | ✓ | — | — | — | ∼ |
| Capability-aware route filtering | ✓ | — | — | — | — | — | — | — |
| Policy & Governance | ||||||||
| Policy-as-Code engine (YAML DSL) | ✓ | — | — | ∼ | — | — | — | — |
| Policy dry-run before activation | ✓ | — | — | — | — | — | — | — |
| Policy versioning + rollback | ✓ | — | — | ∼ | — | — | — | — |
| RBAC + ABAC access control | ✓ | — | ∼ | ✓ | — | — | ✓ | — |
| SSO (OIDC / SAML) | ✓ | — | ✓ | ✓ | — | ✓ | ✓ | — |
| PII & Data Protection | ||||||||
| PII detection + redaction (LLM + MCP) | ✓ | — | — | — | — | — | — | — |
| DLP custom patterns per tenant | ✓ | — | — | — | — | — | — | — |
| Reversible tokenisation | ✓ | — | — | — | — | — | — | — |
| EU data residency guaranteed | ✓ | — | — | ∼ | — | — | ∼ | — |
| Right to erasure (GDPR) | ✓ | — | — | — | — | — | — | — |
| MCP Proxy & Tool Governance | ||||||||
| MCP tool calls proxied & governed | ✓ | — | — | — | — | — | — | — |
| MCP server registry + credential store | ✓ | — | — | — | — | — | — | — |
| MCP argument-level policy rules | ✓ | — | — | — | — | — | — | — |
| MCP PII scanning (args + response) | ✓ | — | — | — | — | — | — | — |
| MCP rate limiting + circuit breaker | ✓ | — | — | — | — | — | — | — |
| Agentic AI Governance | ||||||||
| Human approval gate (enforced at exec) | ✓ | — | — | — | — | — | — | — |
| Agent loop detection + kill switch | ✓ | — | — | — | — | — | — | — |
| Multi-agent session tracking | ✓ | — | — | — | — | — | — | — |
| Full OTel trace: LLM turns + MCP calls | ✓ | — | ∼ | — | — | ∼ | — | — |
| Audit & Compliance | ||||||||
| Immutable HMAC-signed audit log | ✓ | — | — | — | — | — | ∼ | — |
| SOC2 / HIPAA / GDPR evidence packages | ✓ | — | — | — | — | — | ∼ | — |
| EU AI Act compliance engine | ✓ | — | — | — | — | — | — | — |
| SIEM export (Splunk, CloudWatch, Elastic) | ✓ | — | ∼ | ∼ | — | ∼ | ✓ | — |
| Scheduled compliance reports (PDF + JSON) | ✓ | — | — | — | — | — | — | — |
| FinOps & Cost Control | ||||||||
| Real-time cost per request (USD) | ✓ | ✓ | ✓ | — | — | ✓ | ∼ | — |
| Budget caps (soft + hard) per tenant | ✓ | ∼ | ∼ | — | — | ∼ | — | — |
| Auto model downgrade on budget threshold | ✓ | — | — | — | — | — | — | — |
| Chargeback reports per tenant/team | ✓ | — | ∼ | — | — | ∼ | — | — |
| Guardrails & Safety | ||||||||
| Prompt firewall (pre + post filter pipeline) | ✓ | — | ∼ | ∼ | ∼ | — | ✓ | — |
| Jailbreak detection | ✓ | — | ∼ | — | — | — | ✓ | — |
| Output sanitization (XSS, SQLi, SSRF) | ✓ | — | — | — | — | — | — | — |
| System prompt leakage detection | ✓ | — | — | — | — | — | — | — |
| Content policy filters per tenant | ✓ | — | ∼ | — | ∼ | — | ✓ | — |
| Deployment & Infrastructure | ||||||||
| Air-gapped / on-prem deployment | ✓ | ∼ | — | ✓ | — | — | — | — |
| Zero-dependency standalone mode | ✓ | — | — | — | — | — | — | — |
| Multi-region active-active | ✓ | — | ∼ | ✓ | ✓ | — | ✓ | — |
| Kubernetes Helm chart + HPA | ✓ | ✓ | ∼ | ✓ | — | — | — | — |
| Hot config propagation (< 5s) | ✓ | — | — | ∼ | — | — | — | — |
| Observability | ||||||||
| Prometheus metrics + Grafana dashboards | ✓ | ✓ | ∼ | ✓ | — | ∼ | ∼ | — |
| OpenTelemetry distributed tracing | ✓ | ∼ | ∼ | ∼ | — | — | ∼ | — |
| Per-tenant analytics | ✓ | ∼ | ✓ | — | — | ✓ | ∼ | — |
| Anomaly detection for traffic patterns | ✓ | — | — | — | — | — | — | — |
Developers Love It. Compliance Requires It.
Every stakeholder gets exactly what they need from the same platform.
One endpoint. Drop-in compatibility. Route to any provider with automatic failover. Add streaming, rate limiting, and observability in minutes.
Two governed data planes, one control plane. AI gateway at the edge, tool proxy inside the perimeter. Adopt incrementally — add tool governance when agents go to production.
Immutable audit trail with tamper-evident signatures. PII detected and redacted before reaching providers. Compliance evidence packages generated on demand.
Hard policy enforcement at the gateway. PII blocked before it leaves your network. Role-based access to authorised models only. Every request logged and auditable.
Real-time cost tracking per request. Budget caps that automatically enforce. Monthly chargeback reports. Smart caching reduces repeated token spend by up to 40%.
Two governed data planes — AI at the edge, tools inside the perimeter — managed as one. Production-grade performance. Enterprise-ready from day one.
Start Your Free 30-Day Trial
Full access to all features. No credit card required. Set up in under 60 seconds.
Simple, Transparent Pricing
Every plan includes the full platform. Pick the tier that matches your scale. No per-pod charges. No surprise invoices.
| Free Trial | Starter | Most PopularGrowth | Scale | Enterprise+ | |
|---|---|---|---|---|---|
| Tenants | Unlimited | 1 – 3 | 4 – 20 | 21 – 100 | 100+ |
| Token Ceiling | Unlimited | 500M / month | 2B / month | 10B / month | Negotiated |
| Deployment | Self-hosted | Self-hosted | Self-hosted | Self-hosted | Self-hosted |
| Support | Community | Standard SLA | Standard SLA | Priority SLA | Dedicated SLA |
| Cloud Managed | Coming Soon | Coming Soon | Coming Soon | Coming Soon | Coming Soon |
| Volume Discounts | — | — | — | ✓ | ✓ |
| SaaS Reseller Licensing | — | — | — | ✓ | ✓ |
| Dedicated Success Manager | — | — | — | ✓ | ✓ |
| Custom Integrations | — | — | — | ✓ | ✓ |
| On-Site Onboarding | — | — | — | — | ✓ |
| Best For | Evaluate all features for 30 days | First production deployment. Single team. | Platform team governing multiple teams. | Large enterprise or internal AI platform. | Global enterprise. Financial services. Government. |
| Start Free Trial | Talk to Sales | Talk to Sales | Talk to Sales | Talk to Sales |
Add-On Modules
See It in Action.
Start Your Free Trial Today.
Full access for 30 days. No credit card. Deploy in 60 seconds and see governance working on your first request.