TokenZero vs Envoy AI Gateway
Envoy AI Gateway is an Envoy-based gateway for Kubernetes that routes to model providers with token-based rate limiting, provider fallback and an MCP proxy. The matrix below says what each product is and how it bills; the only numbers are TokenZero's own measurements and prices.
TokenZero and Envoy AI Gateway differ in kind: Envoy AI Gateway is Kubernetes AI gateway; TokenZero is a BYOK gateway whose engines reduce the provider bill and sign a receipt per call. Measured overhead is 1.52 ms p50; the cascade holds a 99.8% parity floor.
· Source: Envoy AI Gateway documentation at https://aigateway.envoyproxy.io/ read 2026-10-26; TokenZero overhead from /benchmarks; prices from table 2026-10-26
At a glance
- Compared with
- Envoy AI Gateway (Kubernetes AI gateway)
- TokenZero overhead
- 1.52 ms p50 / 3.42 ms p95 (measured, /benchmarks)
- BYOK
- TokenZero: always · Envoy AI Gateway: yes
- Receipts
- TokenZero: signed per call · Envoy AI Gateway: none
- Billing
- TokenZero: 15% of verified savings · Envoy AI Gateway: open source
- Reference saving (gpt-6.1-sol, 100k calls)
- $285/month from prefix caching (computed)
- Net after 15% fee
- $242/month (computed)
- Parity floor
- 99.8%
- Free tier
- $500/month routed
- Vendor page read
- 2026-10-26
TokenZero vs Envoy AI Gateway: what each one is (vendor page read 2026-10-26)
| Dimension | TokenZero | Envoy AI Gateway |
|---|---|---|
| Category | BYOK savings gateway | Kubernetes AI gateway |
| Hosting | hosted | self-hosted (Kubernetes) |
| Bring your own key | always; keys pass through and are never stored | yes |
| Open source | CLI, MCP server, audit core and GitHub Action Apache-2.0; gateway hosted | Apache-2.0 |
| How it bills | free up to $500/month routed; then 15% of verified savings, 3x-ROI-or-$0, capped plans | open source |
| Caching | prompt-cache formatting + exact and semantic response cache | none built in (external cache via Envoy) |
| Routing | cascade to the cheaper sibling inside one provider, 99.8% parity floor, advisory by default | provider fallback and load balancing you configure |
| Savings receipts | Ed25519-signed per call, hash-chained, public key published | none |
| Gateway overhead | 1.52 ms p50 / 3.42 ms p95 (measured, /benchmarks) | not measured by TokenZero |
| Data retention | metadata only; ZDR mode available | see vendor docs |
| Net saving, 100k gpt-6.1-sol calls/month (prefix caching only) | $242 after fee | — |
What you keep when you move from Envoy AI Gateway
your Envoy and Kubernetes setup; TokenZero is an upstream backend.
- Hosted and stateless: no proxy to deploy, patch or upgrade.
- Cost engines (prefix-cache formatting, response cache, cascade with a parity floor) rather than traffic policy.
- Signed receipts per call.
The change
OPENAI_BASE_URL=https://tokenzero.sh/v1
ANTHROPIC_BASE_URL=https://tokenzero.sh
# keep your provider keys exactly as they areThen npx -y @tokenzero/cli doctor to confirm the gateway, signer and pricing table.
Questions people ask
What is the difference between TokenZero and Envoy AI Gateway?
Envoy AI Gateway is an Envoy-based gateway for Kubernetes that routes to model providers with token-based rate limiting, provider fallback and an MCP proxy. TokenZero is a BYOK gateway: you keep your Envoy and Kubernetes setup; TokenZero is an upstream backend, and every call comes back with a signed receipt. Hosted and stateless: no proxy to deploy, patch or upgrade.
What does switching from Envoy AI Gateway to TokenZero save?
It depends on your prompts; on the reference workload (100,000 calls of 2,000 input with a 1,500-token static prefix and 300 output on gpt-6.1-sol, table 2026-10-26) prefix caching alone cuts $700 to $415 a month, $285 saved and $242 net after the 15% fee; exact-cache hits and cascade routing add to that. The receipts show the real figure.
Can I keep Envoy AI Gateway and add TokenZero?
Usually yes: chain them by pointing Envoy AI Gateway's upstream at https://tokenzero.sh (or TokenZero's X-TokenZero-Upstream at Envoy AI Gateway); the receipt still prices the request at list and records what the gateway did.
How is the 15% fee computed?
On verified savings only: list-price baseline minus provider-reported actual cost, per signed receipt. A cycle whose savings are below 3x the fee is billed $0; Pro Cap and Scale Cap add monthly ceilings. The first $500 of routed spend each month is free.