Provider-level failover
Keep eligible traffic running by switching to another compatible provider for the same model when a route becomes unavailable.
Resilient AI infrastructure for production
CostRouter Enterprise
One enterprise gateway for multi-model access, provider failover, policy controls, and auditable spend.
Provider-level failover
Keep eligible traffic running by switching to another compatible provider for the same model when a route becomes unavailable.
Models aligned to your roadmap
Source models beyond the public catalog by use case, region, and capacity.
No prompt or output retention
We retain only the usage records required for billing and reconciliation. Prompts, files, request bodies, and model outputs are not stored.
Enterprise control plane
Enterprise AI control
Routing, access, governance, and spend controls in one auditable service layer.
Models aligned to your roadmap
Source models beyond the public catalog by use case, region, and capacity.
No prompt or output retention
We retain only the usage records required for billing and reconciliation. Prompts, files, request bodies, and model outputs are not stored.
Usage-based commercial terms
Align pricing to model mix, volume, reserved capacity, and support.
API key policy controls
Set spend, expiry, model, IP, and routing policies per API key.
Request-level billing transparency
Track the model, token usage, charges, refunds, status, and request ID for every API request.
Multi-provider resilience
Resilient multi-provider routing
Route eligible requests across compatible providers by availability, latency, price, region, and policy.
- 01
Validate
API key, endpoint, model, and account policy.
- 02
Match
Same model, compatible provider and request format.
- 03
Select
Availability, latency, price, region, and policy.
- 04
Fail over
Reroute eligible traffic and preserve usage records.
Explicit failover boundary
Failover requires an available compatible route to the same requested model; it does not cover provider-wide model outages.
Enterprise procurement
Enterprise procurement and billing
Cards, wallets, bank transfer, invoices, and request-level records in one commercial workflow.
Payment and invoicing
Online payments
Major cards and supported digital wallets via Stripe.
Corporate bank transfer
Company-to-company settlement for approved accounts.
Business invoices
Invoices backed by detailed usage and billing records.
Transparent pricing
- Published unit rates for self-service models
- Pay only for recorded usage
- No long-term contract required for standard usage
- Volume discounts available through enterprise sales
- Request-level usage and billing records
Reserved capacity, dedicated resources, or custom delivery arrangements may be governed by separately agreed commercial terms.
Infrastructure & Operations
Dedicated AI infrastructure
CostRouter-owned GPU capacity complements our multi-provider routing network.
Hong Kong office
Physical office for our product, operations, sales, and customer support teams.
Production data centers
Resilient power, cooling, network connectivity, and on-site operations.
CostRouter-owned GPU capacity
Physical NVIDIA GPUs for selected inference, training, and dedicated compute.
On-site operations
Inspection and maintenance by technical personnel.
The photographs and equipment shown were captured on site by CostRouter. Infrastructure availability and the scope of dedicated capacity are confirmed through the enterprise proposal.
Company profile
Hong Kong-incorporated company
Physical office, accountable contacts, and formal B2B contracting.
- Place of incorporation
- Hong Kong
- Team size
- Approximately 20 team members
- Monthly API transaction volume
- US$800K+
- Physical business address
- Room 721A, 7/F, Star House, 3 Salisbury Road, Tsim Sha Tsui, Hong Kong
Enterprise FAQ
Technical and procurement FAQ
Data handling, model access, resilience, and migration.
Does CostRouter retain prompts or model outputs?
No. We retain usage records required for reconciliation, including model, tokens, charge, status, and request ID; customer content is not stored.
Can we request models outside the public catalog?
Yes. Enterprise sales can assess additional models by compatibility, region, capacity, and commercial feasibility.
How does provider-level failover work?
Eligible traffic can move to another compatible provider serving the same requested model. Availability of an alternate route is required.
Do we need to rewrite our application?
Most compatible SDK and HTTP integrations only require a CostRouter Base URL and API key. More complex routing policies can be introduced incrementally with the implementation team.
Plan your enterprise deployment
Plan your enterprise deployment
Share your models, regions, traffic profile, and requirements. We will prepare a technical and commercial proposal.