TokenZero vs Requesty
Requesty is a hosted router with model routing, caching, guardrails and spend controls behind one API. The matrix below says what each product is and how it bills; the only numbers are TokenZero's own measurements and prices.
TokenZero and Requesty differ in kind: Requesty is LLM router; 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. On 100,000 gpt-6.1-sol calls, prefix caching saves $285 a month, $242 net of the 15% fee.
· Source: Requesty documentation at https://www.requesty.ai/ read 2026-10-26; TokenZero overhead from /benchmarks; prices from table 2026-10-26
At a glance
- Compared with
- Requesty (LLM router)
- TokenZero overhead
- 1.52 ms p50 / 3.42 ms p95 (measured, /benchmarks)
- BYOK
- TokenZero: always · Requesty: varies by plan
- Receipts
- TokenZero: signed per call · Requesty: none
- Billing
- TokenZero: 15% of verified savings · Requesty: usage plans
- 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 Requesty: what each one is (vendor page read 2026-10-26)
| Dimension | TokenZero | Requesty |
|---|---|---|
| Category | BYOK savings gateway | LLM router |
| Hosting | hosted | hosted |
| Bring your own key | always; keys pass through and are never stored | varies by plan |
| Open source | CLI, MCP server, audit core and GitHub Action Apache-2.0; gateway hosted | closed |
| How it bills | free up to $500/month routed; then 15% of verified savings, 3x-ROI-or-$0, capped plans | usage plans |
| Caching | prompt-cache formatting + exact and semantic response cache | response cache |
| Routing | cascade to the cheaper sibling inside one provider, 99.8% parity floor, advisory by default | between providers, by the router |
| 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 Requesty
the request shape; routing becomes explicit and inspectable.
- Routing stays inside one provider, advisory by default, with every decision in headers and on the receipt.
- You keep paying the provider directly; TokenZero bills a share of verified savings.
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 Requesty?
Requesty is a hosted router with model routing, caching, guardrails and spend controls behind one API. TokenZero is a BYOK gateway: you keep the request shape; routing becomes explicit and inspectable, and every call comes back with a signed receipt. Routing stays inside one provider, advisory by default, with every decision in headers and on the receipt.
What does switching from Requesty 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 Requesty and add TokenZero?
Usually yes: chain them by pointing Requesty's upstream at https://tokenzero.sh (or TokenZero's X-TokenZero-Upstream at Requesty); 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.