OpenAI compatible API · Attested · Public status

Portkey Alternative — Routing Without Logging Every Prompt

A Portkey alternative for teams that can't store prompt content. Usage metering without content logs, verifiable in source.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Portkey alternative

Portkey logs every request. TrustedRouter logs none of them — and proves it.

Portkey is built around observability: it captures every request, response, and trace so you can monitor and govern AI usage. That's exactly what you want for some workloads — and exactly what you can't have for sensitive ones.

TrustedRouter takes the opposite stance. Prompt and output bodies are never persisted, the gateway is hardware-attested, and the whole thing is open source. You get routing, fallback, and usage metering without a copy of every prompt sitting in a logging backend.

Try the playground Trust surface

Metadata only — the full log schemaopen source

{
  "model_id": "anthropic/claude-sonnet-4.6",
  "input_tokens": 12,
  "output_tokens": 84,
  "cost_microdollars": 218,
  "provider": "anthropic",
  "region": "us-central1"
}
# No prompt body. No response body. No content.
# Verify the schema in the open-source code.

Usage tracking

Metering without content.

Token counts, cost, latency, model, region — everything you need for billing and capacity, none of the prompt content.

No content logs

By construction, not config.

The attested binary never writes request or response bodies. It isn't a toggle you can forget to set; it's a property of the code you can verify.

Routing + fallback

The gateway features you came for.

30+ providers, automatic rollover on failure, BYOK, prepaid credits — the control-plane conveniences, minus the surveillance.

PortkeyTrustedRouter

Core stanceLog everything for controlLog nothing, prove it

Prompt contentCaptured + storedNever persisted

SourceClosedOpen

Runtime trustHosted policyHardware attestation

Usage meteringYes (full content)Yes (metadata only)

Best fitTeams that want full request observabilityTeams that can't keep prompt copies

Two valid philosophies

Pick by what you're allowed to store.

If you need to replay and inspect every request, an observability-first gateway is the right tool. If a stored copy of a prompt is a liability — PHI, privileged material, proprietary code — you need the opposite: a path that provably keeps nothing.

Why we built around proof: “Attestation is All You Need”.

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

887recent availability samples

Model	Providers	Context	Input	Output	Privacy	Measured route
Anthropic: Claude Opus 4.8`anthropic/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-5.5`openai/gpt-5.5`	4 routes	1,050,000	$5.25/1M	$31.5/1M	ZDR 3 cited scores	Warming up
Google: Gemini 3.5 Flash`google/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 Code`moonshotai/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=14
Z.ai: GLM 5.2`z-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	measured engy · 0.00% available · n=73
MiniMax: MiniMax M3`minimax/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=21