Vercel AI Gateway alternative
Vercel AI Gateway is one endpoint for many providers with budgets, usage views and failover, integrated with the AI SDK. The matrix below says what each product is and how it bills; the only numbers are TokenZero's own measurements and prices.
TokenZero is a BYOK alternative to Vercel AI Gateway: you keep your provider keys and list prices, add 1.52 ms p50 of measured overhead, and every call returns a signed receipt. On 100,000 reference calls on gpt-6.1-sol, cache formatting alone saves $285 a month, $242 net after the 15% fee; Vercel AI Gateway issues no receipts.
· Source: Vercel AI Gateway documentation at https://vercel.com/docs/ai-gateway/usage-and-pricing read 2026-10-26; TokenZero overhead from /benchmarks; prices from table 2026-10-26
At a glance
- Compared with
- Vercel AI Gateway (hosted AI gateway)
- TokenZero overhead
- 1.52 ms p50 / 3.42 ms p95 (measured, /benchmarks)
- BYOK
- TokenZero: always · Vercel AI Gateway: yes
- Receipts
- TokenZero: signed per call · Vercel AI Gateway: none
- Billing
- TokenZero: 15% of verified savings · Vercel AI Gateway: provider list price with no token markup (per Vercel docs)
- 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 Vercel AI Gateway: what each one is (vendor page read 2026-10-26)
| Dimension | TokenZero | Vercel AI Gateway |
|---|---|---|
| Category | BYOK savings gateway | hosted AI gateway |
| Hosting | hosted | hosted (Vercel) |
| 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 | closed |
| How it bills | free up to $500/month routed; then 15% of verified savings, 3x-ROI-or-$0, capped plans | provider list price with no token markup (per Vercel docs) |
| Caching | prompt-cache formatting + exact and semantic response cache | provider caching passed through |
| Routing | cascade to the cheaper sibling inside one provider, 99.8% parity floor, advisory by default | provider failover and model selection |
| 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 Vercel AI Gateway
the AI SDK: createOpenAI / createAnthropic take the TokenZero base URL.
- Prompt-cache formatting, exact and semantic response cache and cascade routing reduce the bill before the provider sees the request.
- A signed receipt per call with the list-price baseline, chained per workspace.
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
Is TokenZero a drop-in alternative to Vercel AI Gateway?
Vercel AI Gateway is one endpoint for many providers with budgets, usage views and failover, integrated with the AI SDK. TokenZero is a BYOK gateway: you keep the AI SDK: createOpenAI / createAnthropic take the TokenZero base URL, and every call comes back with a signed receipt. Prompt-cache formatting, exact and semantic response cache and cascade routing reduce the bill before the provider sees the request.
What does switching from Vercel 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 Vercel AI Gateway and add TokenZero?
Usually yes: chain them by pointing Vercel AI Gateway's upstream at https://tokenzero.sh (or TokenZero's X-TokenZero-Upstream at Vercel 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.