Rafay Systems Enhances AI Spending Control with New Token Router Features
News related to:Rafay Systems · 4 min read
SUNNYVALE, Calif., Nov. 5, 2026 /CourierPR/ -- Rafay Systems, the infrastructure orchestration and monetization platform for neoclouds, telcos, and enterprise AI, has announced the release of new capabilities in its Rafay Token Factory. These new features include the Token Router, a new routing layer that directs inference requests based on optimal models, priority, health, and cost, providing a path to predictable AI spend. The Token Router, which sits between applications and every place inference can run, allows operators to manage where every request runs and what it costs.
The new capabilities are built for two groups: neoclouds delivering open-source models as a service, and enterprises operating internal token factories for their own developers and applications. The Token Router, a new routing layer, sends each request to in-cluster model deployments or to external providers such as OpenAI, Anthropic, and any OpenAI-compatible endpoint, based on priority, health, and cost. Token Budgets let administrators set daily or monthly spending limits for an organization, a project, or an individual user, and enforce them before a request is admitted.
The new features are designed to address the shift in how AI is consumed. Agentic workflows use more tokens per task, resulting in rising total AI bills even as the price per token falls. Teams are moving high-volume work to open-source models to keep spending in check. Operators now need to serve both frontier and open-source models side by side and control what each costs.
Used together, the Token Factory and Token Router let operators offer both frontier models and open-source models behind a single endpoint and shift traffic between them automatically. An enterprise can give its teams a frontier model while their daily budget lasts, then move them to an open-source model running on its own GPUs for the rest of the day, with no change to the applications making the calls.
The new capabilities are built for two groups: neoclouds delivering open-source models as a service, and enterprises operating internal token factories for their own developers and applications. The Token Router, a new routing layer, sends each request to in-cluster model deployments or to external providers such as OpenAI, Anthropic, and any OpenAI-compatible endpoint, based on priority, health, and cost. Token Budgets let administrators set daily or monthly spending limits for an organization, a project, or an individual user, and enforce them before a request is admitted.
The new features are designed to address the shift in how AI is consumed. Agentic workflows use more tokens per task, resulting in rising total AI bills even as the price per token falls. Teams are moving high-volume work to open-source models to keep spending in check. Operators now need to serve both frontier and open-source models side by side and control what each costs.
Used together, the Token Factory and Token Router let operators offer both frontier models and open-source models behind a single endpoint and shift traffic between them automatically. An enterprise can give its teams a frontier model while their daily budget lasts, then move them to an open-source model running on its own GPUs for the rest of the day, with no change to the applications making the calls.
The new features are designed to address the shift in how AI is consumed. Agentic workflows use more tokens per task, resulting in rising total AI bills even as the price per token falls. Teams are moving high-volume work to open-source models to keep spending in check. Operators now need to serve both frontier and open-source models side by side and control what each costs.
Used together, the Token Factory and Token Router let operators offer both frontier models and open-source models behind a single endpoint and shift traffic between them automatically. An enterprise can give its teams a frontier model while their daily budget lasts, then move them to an open-source model running on its own GPUs for the rest of the day, with no change to the applications making the calls.
Rafay Systems is now enabling neoclouds to deliver open-source models as a service, and enterprises to operate internal token factories for their own developers and applications. The new capabilities are built for two groups: neoclouds delivering open-source models as a service, and enterprises operating internal token factories for their own developers and applications. The Token Router, a new routing layer, sends each request to in-cluster model deployments or to external providers such as OpenAI, Anthropic, and any OpenAI-compatible endpoint, based on priority, health, and cost. Token Budgets let administrators set daily or monthly spending limits for an organization, a project, or an individual user, and enforce them before a request is admitted.
The new features are designed to address the shift in how AI is consumed. Agentic workflows use more tokens per task, resulting in rising total AI bills even as the price per token falls. Teams are moving high-volume work to open-source models to keep spending in check. Operators now need to serve both frontier and open-source models side by side and control what each costs.
Used together, the Token Factory and Token Router let operators offer both frontier models and open-source models behind a single endpoint and shift traffic between them automatically. An enterprise can give its teams a frontier model while their daily budget lasts, then move them to an open-source model running on its own GPUs for the rest of the day, with no change to the applications making the calls.