LUNAROUTEenterprise
Book a demo
Lunaroute enterprise

Private inference.
On your terms.

Two ways to scale with LunaRoute: a unified gateway over the providers you choose, and private inference that squeezes more throughput out of dedicated servers you control.

▸one gateway: BYO keys or use our providers
▸private inference scheduler for dedicated GPUs
▸budgets & policy by user, team, key or workload
Book a demosee the architecture ↓
MARE SERENITATIS
ONE GATEWAY · EVERY ROUTE
OCEANUS PROCELLARUM
PRIVATE DEDICATED CAPACITY
MARE NUBIUM
SCHEDULER · LEDGER · NO LOGS
The gateway

One gateway for the providers your teams already use.

Connect your own provider accounts through LunaRoute, alongside our curated open-weight models. External provider access and charges are separate from the fixed-cost inference plans. Teams get one OpenAI-compatible endpoint, finance gets one ledger, and platform engineering gets policy that follows users, keys, agents, and workloads.

▸BYO provider keys, LunaRoute-hosted providers, or both
▸budgets by user, team, key, CI job, or workload
▸failover and routing without changing agent config
▸one ledger for public and private inference spend
▸agent tools over MCP — web search, document conversion with OCR, image generation and editing — on the same key, with per-member tool policy and every call in the ledger
enterprise-gateway — topology
teams + agents
   |
   |  OpenAI-compatible or Anthropic-compatible requests
   v
+--------------------------+
| LUNAROUTE ENTERPRISE    |
|  |- policy + budgets     |
|  |- routing + failover   |
|  '- ledger + accounting  |
+-----------+--------------+
            |
  +---------+---------+---------+
  v                   v         v
BYO keys         LunaRoute   private
providers        providers  inference
Private inference

Private inference, without idle dedicated GPUs.

Bring dedicated capacity under the same gateway. LunaRoute can run private models on servers you control, route sensitive workloads there first, and spill only the traffic you allow.

Models we can support well

Our curated open-weight models include GLM 5.3, GLM 5.3 Flash, and DeepSeek 4.1 Flash. We add models when we can support them well.

Dedicated deployments and external provider accounts are scoped separately for your organization.

Single-tenant servers
Dedicated GPUs, dedicated caches, and deployment boundaries that match your risk model.
Gateway policy stays central
Keep users on one endpoint while routing sensitive workloads to your private fleet.
Utilization without routing sprawl
Keep dedicated capacity busy through the same gateway policy, ledger, and scheduler instead of sending teams to separate endpoints.
The scheduler

Idle GPUs are expensive GPUs.

Once the rig is a fixed cost, utilization is savings. LunaRoute gives priority requests preferential access, uses spare capacity for overflow, and queues excess work within your configured limits.

scheduler — live
$ lunaroute-cli sched status srv-east-1

srv-east-1   8 x B200   single-tenant

admission cap ............... max_in_flight = 64
efficient target ............ b_star = 56
backend waiting ceiling ..... 0

priority requests .......... preferential access
overflow requests .......... available capacity
busy periods ............... additional wait time

capacity rule ............... never admit past max_in_flight
gap fill .................... use spare capacity, yield on deadline risk
▸
Priority concurrency
Give time-sensitive requests preferential access. Additional requests use available capacity and may wait longer during busy periods.
▸
Capacity controls
Set concurrent request limits around your dedicated capacity and the workloads you need to support.
▸
Queues and timeouts
Excess work waits in the scheduler queue or fails fast when the configured deadline can no longer be met.
▸
Overflow capacity
Use spare capacity for additional requests. Scheduling and any performance commitments are defined in your Enterprise agreement.
Data & privacy

NO LOGS, at enterprise scale.

The same posture as the public product, contractually: request and response bodies are processed in memory and never stored by LunaRoute. On private inference, traffic stays on your single-tenant path.

No request-body storage
Prompts and completions are never written to disk by LunaRoute. We keep timestamps, model, token counts and cost - your ledger.
Single-tenant isolation
Dedicated servers are yours alone - no shared GPUs, no shared caches, no co-mingled traffic.

Let's size your fleet.

Tell us your models, your traffic, and whether you're bringing GPUs or renting ours. We'll map it to a gateway + private inference plan.

Book a demoSee the Teams planexplore self-serve plans