the platform

15 capabilities, one decision point.

Your agents call models and tools all day, and every one of those calls is a decision somebody should be able to account for. Before anything leaves your network, Token Observe resolves the request against a record of who owns that agent, checks it against an action-level permission set, scans it for personal data, secrets and prompt injection, prices it against a hard budget, and then allows, redacts, blocks or parks it for a named human. These 15 capabilities are how that decision gets made, how it gets proved afterwards, and how it reaches past the model call to the tools, the effects and the traffic that never came through the gateway at all.
Capabilities
15
Steps in the governed request path
11
Model providers under one policy set
6
Process, one database, one file to back up
1

See the estate

What AI costs the business, what it is being asked to do, and which of it anybody actually approved. These three answer the questions the product leads with, and none of them requires you to route a single agent through a gateway first.

Know and authorise

The record of which agents exist and what each one may do. Nothing below this line means anything without it: a policy that fires on an agent nobody owns produces an alert nobody actions.

Decide and enforce

The inline decision point. Every governed request is allowed, blocked, redacted or parked for a human before it leaves your network, and every policy can run in shadow mode first so you learn your false-positive rate before you start blocking real work.

Route and prove

Six model providers behind one set of policies, and a searchable, hash-chained record of what each governed request did. The equivalence across providers is enforced by test, because a policy that fires on OpenAI but not on Gemini is worse than no policy.

Reach further than the model call

Tools, external effects, subscription seats and the traffic that never came through the gateway at all. This is where most agent risk actually sits, and where a gateway that only sees model calls stops being able to help.

what it costs to adopt

All 15 arrive with one environment variable.

From that moment the agent has an identity, a budget, a permission set, and a searchable record of each governed request.

Point an agent at Token Observe by changing one environment variable
OPENAI_BASE_URL="https://tokenobserve.company.com/v1"     # was https://api.openai.com/v1
ANTHROPIC_BASE_URL="https://tokenobserve.company.com"     # was https://api.anthropic.com

A base-URL change is the normal case for the OpenAI-compatible, Anthropic and Gemini dialects. Whether your own SDK and version behave that way is the first thing to check, and the first thing a proof of concept settles.

OpenAI
Chat Completions, Responses and embeddings
Anthropic
Messages, including the x-api-key dialect
Google Gemini
Native Gemini ingress
OpenRouter
With caller-controlled route selectors refused before egress
Amazon Bedrock
For estates that will not egress to a model vendor directly
Azure OpenAI
Deployment-name routing under the same policies
Your own endpoint
Any OpenAI-compatible endpoint you host

The same policies, redaction, budgets and tracing apply identically whichever provider serves the request, and that equivalence is enforced by a test over every provider kind rather than asserted here.

See the request path
get in touch

Which of the 15 is the one you actually need?

Most estates need three or four of these and can defer the rest. Describe what your agents do and which of them worries you, and you will get a straight answer about where to start — including when the answer is that you do not need a control plane yet.

no form · no qualification step · no sales desk · the other three ways in