TokenVue
Route, secure, monitor, and control costs for every major LLM.
TokenVue is an AI gateway that sits between application code and large language model providers, offering unified routing, security guardrails, cost tracking, and observability. It supports OpenAI, Anthropic, Gemini, Mistral, DeepSeek, Cohere, and other providers through a single OpenAI-compatible API. Teams can enforce PII redaction, prompt injection protection, budget limits, and RBAC across all AI traffic from one control plane.
TokenVue acts as a drop-in proxy gateway that intercepts all LLM API calls, applying configurable routing rules, guardrails, budget enforcement, and logging before forwarding requests to the appropriate provider.
AI engineering teams, SaaS builders, and enterprises running production LLM workloads
Background.
- Status
- launched
- Business model
- freemium
Contact
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.