Verified daily · Last run: 2026-06-16 16:05 UTC

How we prove it

Four promises, each one independently verifiable. If any check fails, your billing period is refunded — no ticket, no arguments.

🔀

1. One model name → one official upstream

claude-* goes to Anthropic. gpt-* goes to OpenAI. gemini-* goes to Google. No distilled clones, no silent downgrades under load.

no substitution
🪞

2. No prompt injection, no response rewriting

Your request body is forwarded byte-for-byte. The only edits are auth key swap and (optional, opt-in) schema translation between OpenAI and Anthropic protocols.

byte-identical
📏

3. Daily benchmark parity, published raw

Every 24 hours we run MMLU-Pro / GSM8K / HumanEval samples via VoltAI and via direct upstream. We publish the delta. Target ≤ 1.5%.

Δ ≤ 1.5%
🔐

4. Bring your own key (zero-trust)

Enterprise plans let you configure your own upstream provider keys. VoltAI then only handles auth, metering, rate-limiting — we never see the model output.

zero-trust

Today's parity snapshot

Auto-generated at 00:05 UTC. Numbers below are current live readings. Raw eval logs at github.com/voltai/integrity-eval.

ModelUpstreamMMLU-ProGSM8KHumanEvalΔ vs directStatus
DeepSeek APIDeepSeek90.0% / 90.0%+0.00pppass
Claude familyAnthropicpending
ChatGPT / GPT familyOpenAIpending
Gemini familyGooglepending
Open-source deploymentsVoltAI-owned hardwarepending

Don't trust us — verify us.

Grab $5 free credit and run your own eval. Our public eval repo reproduces every number you see above. If our numbers don't match yours, we refund.