TokenZero vs Amazon Bedrock (as a gateway)
Amazon Bedrock (as a gateway) is managed access to many models inside AWS with guardrails, IAM and CloudWatch. The matrix below says what each product is and how it bills; the only numbers are TokenZero's own measurements and prices.
TokenZero and Amazon Bedrock (as a gateway) differ in kind: Amazon Bedrock (as a gateway) is cloud model platform; 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: Amazon Bedrock (as a gateway) documentation at https://aws.amazon.com/bedrock/pricing/ read 2026-10-26; TokenZero overhead from /benchmarks; prices from table 2026-10-26
At a glance
- Compared with
- Amazon Bedrock (as a gateway) (cloud model platform)
- TokenZero overhead
- 1.52 ms p50 / 3.42 ms p95 (measured, /benchmarks)
- BYOK
- TokenZero: always · Amazon Bedrock (as a gateway): AWS account billing
- Receipts
- TokenZero: signed per call · Amazon Bedrock (as a gateway): none (CloudWatch metrics)
- Billing
- TokenZero: 15% of verified savings · Amazon Bedrock (as a gateway): provider token prices through AWS; platform services billed by AWS
- 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 Amazon Bedrock (as a gateway): what each one is (vendor page read 2026-10-26)
| Dimension | TokenZero | Amazon Bedrock (as a gateway) |
|---|---|---|
| Category | BYOK savings gateway | cloud model platform |
| Hosting | hosted | AWS |
| Bring your own key | always; keys pass through and are never stored | AWS account billing |
| 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 token prices through AWS; platform services billed by AWS |
| Caching | prompt-cache formatting + exact and semantic response cache | prompt caching on supported models |
| Routing | cascade to the cheaper sibling inside one provider, 99.8% parity floor, advisory by default | intelligent prompt routing within a model family |
| Savings receipts | Ed25519-signed per call, hash-chained, public key published | none (CloudWatch metrics) |
| 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 Amazon Bedrock (as a gateway)
Bedrock model ids: TokenZero normalises them to the provider catalogue for pricing.
- Provider-direct keys at list price with a signed receipt per call, outside any one cloud.
- Cache formatting, response cache and cascade routing work the same across OpenAI, Anthropic, Gemini, xAI and DeepSeek.
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 Amazon Bedrock (as a gateway)?
Amazon Bedrock (as a gateway) is managed access to many models inside AWS with guardrails, IAM and CloudWatch. TokenZero is a BYOK gateway: you keep Bedrock model ids: TokenZero normalises them to the provider catalogue for pricing, and every call comes back with a signed receipt. Provider-direct keys at list price with a signed receipt per call, outside any one cloud.
What does switching from Amazon Bedrock (as a 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 Amazon Bedrock (as a gateway) and add TokenZero?
Usually yes: chain them by pointing Amazon Bedrock (as a gateway)'s upstream at https://tokenzero.sh (or TokenZero's X-TokenZero-Upstream at Amazon Bedrock (as a 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.