OpenAI compatible API · Attested · Public status

Zero Data Retention LLM API — Verifiable in Source

Zero data retention as a structural property of the open-source code, not just a contract clause. Multi-provider routing with the same posture.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Zero data retention

Zero data retention as a verifiable property, not a contract clause.

"ZDR" usually means a clause in your enterprise agreement. The operator promises not to retain. You hope they comply.

TrustedRouter's prompt path never writes request or response bodies to persistent storage. The code that handles your prompts is open-source. The image hash is published. You can verify that retention is zero — without trusting us.

Try the playground Trust surface

What gets logged — schemaopen source
# Per-request record (token counts, timing, model id)
{
  "request_id": "req_...",
  "workspace_id": "...",
  "model_id": "anthropic/claude-sonnet-4.6",
  "input_tokens": 12,
  "output_tokens": 84,
  "cost_microdollars": 218,
  "provider": "anthropic",
  "region": "us-central1",
  "created_at": "..."
}
# What's NOT in here:
#   - prompt body
#   - response body
#   - user inputs of any kind
# Audit the schema:
#   github.com/.../storage_models.py
Structural

Zero, by construction.

The attested binary doesn't open a write handle to a prompt path. The retention isn't a policy choice; it's a structural property of the code.

Verifiable

Check it yourself.

Grep the source for any code that touches request bodies. There isn't any. The image hash you build is the hash the enclave reports.

End-to-end

Including upstream where possible.

For providers with their own ZDR posture (Anthropic, OpenAI Enterprise, Tinfoil, GCP Confidential), we route under their stronger guarantees and surface that on each model page.

Typical ZDR clauseTrustedRouter
EnforcementContractualStructural — in source
Audit pathSOC 2 + breach disclosureRead the open-source binary + hash check
Operator privilegeOperator can change behaviorOperator can't change without breaking attestation
Multi-providerPer-provider negotiationOne TR contract, route across providers
Self-hostUsually not availableYes — same attestation chain
The honest limits

What ZDR doesn't cover.

Upstream providers have their own retention behavior. We can route to providers that match your posture and we publish each one's known stance on the model pages.

Attestation proves the running binary is the published binary. It doesn't prove the binary is bug-free.

If you can't trust the GCP Confidential Space attestation chain at all, hosted attestation doesn't save you. Self-hosting lets you pin and publish your own image digest under your own controls.

Live catalog evidence

Current routes, prices, privacy, and measured performance.

Catalog facts come from the routes currently configured in TrustedRouter. Performance uses the same cached metadata snapshot as the public leaderboard. Prompts and outputs are not part of these measurements.

392public models
49providers
1270configured routes
250ZDR routes
8provider E2EE routes
1071recent availability samples
Model Providers Context Input Output Privacy Measured route
Anthropic: Claude Opus 4.8anthropic/claude-opus-4.8
3 routes
1,000,000 $5.25/1M $26.25/1M varies 5 cited scores 1598 ms TTFT anthropic · 100.00% available · n=5
OpenAI: GPT-5.5openai/gpt-5.5
4 routes
1,050,000 $5.25/1M $31.5/1M ZDR 3 cited scores Warming up
Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash
+1
7 routes
1,048,576 $1.575/1M $9.45/1M ZDR measured google-ai-studio · 0.00% available · n=14
MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code
+8
19 routes
262,144 $0.735/1M to $0.9975/1M $3.675/1M to $4.2/1M ZDR 5 cited scores measured inceptron · 0.00% available · n=16
Z.ai: GLM 5.2z-ai/glm-5.2
+22
45 routes
1,048,576 $0.714/1M to $1.575/1M $1.575/1M to $5.5125/1M E2EE 4 cited scores 2657 ms TTFT phala · 100.00% available · n=91
MiniMax: MiniMax M3minimax/minimax-m3
+8
21 routes
1,048,576 $0.2835/1M to $0.63/1M $1.155/1M to $2.52/1M ZDR 4 cited scores 2056 ms TTFT wafer · 100.00% available · n=24
AnthropicPolicy varies 12 models 1807 ms p50 · n=27
GMI CloudPolicy varies 53 models 2549 ms p50 · n=16
OpenAIZDR on prepaid 33 models 1337 ms p50 · n=29
Atlas CloudPolicy varies 73 models measured · n=25
Google AI StudioPolicy varies 11 models measured · n=28
Google Vertex AIZDR on prepaid 9 models measured · n=29
Lightning AIPolicy varies 17 models 1429 ms p50 · n=26
KimiPolicy varies 11 models 1365 ms p50 · n=26

Browse every modelReview provider policiesOpen the full leaderboardSnapshot 2026-08-05T03:33:05Z

Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.