evals and logging with an AI proxy · vendor page read 2026-10-26 · prices table 2026-10-26

Braintrust alternative

Braintrust is an evaluation platform with datasets, scorers, logging and a caching proxy. 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 Braintrust: 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; Braintrust issues no receipts.

· Source: Braintrust documentation at https://www.braintrust.dev/pricing read 2026-10-26; TokenZero overhead from /benchmarks; prices from table 2026-10-26

At a glance

Compared with
Braintrust (evals and logging with an AI proxy)
TokenZero overhead
1.52 ms p50 / 3.42 ms p95 (measured, /benchmarks)
BYOK
TokenZero: always · Braintrust: yes (proxy)
Receipts
TokenZero: signed per call · Braintrust: none
Billing
TokenZero: 15% of verified savings · Braintrust: free tier, then 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 Braintrust: what each one is (vendor page read 2026-10-26)

DimensionTokenZeroBraintrust
CategoryBYOK savings gatewayevals and logging with an AI proxy
Hostinghostedhosted; hybrid deployment
Bring your own keyalways; keys pass through and are never storedyes (proxy)
Open sourceCLI, MCP server, audit core and GitHub Action Apache-2.0; gateway hostedproxy open source
How it billsfree up to $500/month routed; then 15% of verified savings, 3x-ROI-or-$0, capped plansfree tier, then usage plans
Cachingprompt-cache formatting + exact and semantic response cacheproxy cache
Routingcascade to the cheaper sibling inside one provider, 99.8% parity floor, advisory by defaultnone
Savings receiptsEd25519-signed per call, hash-chained, public key publishednone
Gateway overhead1.52 ms p50 / 3.42 ms p95 (measured, /benchmarks)not measured by TokenZero
Data retentionmetadata only; ZDR mode availablesee vendor docs
Net saving, 100k gpt-6.1-sol calls/month (prefix caching only)$242 after fee—

What you keep when you move from Braintrust

evals and datasets; only the proxy base URL changes.

  • Shadow parity is an in-production eval of cascade routing: a sample of routed requests is re-run on the original model and a pair is auto-disabled when parity drops.
  • Receipts, not logs: metadata only, signed.

The change

OPENAI_BASE_URL=https://tokenzero.sh/v1
ANTHROPIC_BASE_URL=https://tokenzero.sh
# keep your provider keys exactly as they are

Then npx -y @tokenzero/cli doctor to confirm the gateway, signer and pricing table, and see the switch guide.

Questions people ask

Is TokenZero a drop-in alternative to Braintrust?

Braintrust is an evaluation platform with datasets, scorers, logging and a caching proxy. TokenZero is a BYOK gateway: you keep evals and datasets; only the proxy base URL changes, and every call comes back with a signed receipt. Shadow parity is an in-production eval of cascade routing: a sample of routed requests is re-run on the original model and a pair is auto-disabled when parity drops.

What does switching from Braintrust 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 Braintrust and add TokenZero?

Yes. Braintrust is not a transport-level proxy, so it keeps working unchanged; TokenZero changes only the base URL your SDK calls.

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.

Related

Price your own workload through TokenZero

Moving off Braintrust? Swap base_url in 30 seconds, keep your keys, and let the first receipt show the saving.Start free