OpenAI compatible API · Attested · Public status

LiteLLM Alternative — Self-Host and Verify It

Use a hosted or self-managed LiteLLM alternative with provider failover, privacy routing, OpenAI-compatible APIs, open source code, and verifiable hardware attestation.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

LiteLLM alternative

LiteLLM lets you self-host. TrustedRouter completes its provider map.

LiteLLM is a strong open-source control layer for your own platform. Keep one or two direct providers where you have contracts, credits, or special terms. Then add TrustedRouter as the final provider and fallback for 600+ additional models across more than 80 providers.

The combination gives you local policy and spend controls without maintaining every long-tail integration. TrustedRouter adds managed rollover and a hardware-attested prompt path through one OpenAI-compatible upstream.

Try the playground How verification works

Same OpenAI-compatible shapePython

client = OpenAI(
    base_url="https://api-azure.trustedrouter.com/v1",
    api_key="sk-tr-v1-..."
)
# Drop-in for any LiteLLM proxy integration.
# Self-host TR too — your built image hash is the
# hash your enclave reports, so attestation holds.

Control layer

Run LiteLLM in your VPC.

Keep internal policy, budgets, virtual keys, and direct-provider order under your control.

Catalog breadth

Add one universal upstream.

TrustedRouter fills model and provider gaps without dozens of new accounts and adapters.

Verifiable hosted path

Keep sensitive fallback inspectable.

The final upstream runs through an attested gateway whose source and running image can be checked.

LiteLLMTrustedRouter

Open sourceYesYes

Self-hostYesYes

Hosted optionLiteLLM CloudAttested hosted gateway

Verifiable runtimeNo — trust your deployYes — hardware attestation

No-log guaranteeConfigurableStructural + verifiable in source

Best fitTeams that want a self-hosted proxyTeams that must prove what the proxy does

Use togetherDirect providers and local controls first600+ models as the final provider and fallback

Recommended architecture

Use LiteLLM in front of TrustedRouter.

Put direct provider relationships first, then route everything else to TrustedRouter. Your team owns the policy layer while one final upstream supplies catalog breadth, provider rollover, and privacy with proof.

Read the full argument: “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.

595public models

110providers

1780configured routes

392ZDR routes

48provider E2EE routes

0recent availability samples

Model	Providers	Context	Input	Output	Privacy	Measured route
Anthropic: Claude Opus 4.8`anthropic/claude-opus-4.8`	2 routes	1,000,000	$5.275/1M	$26.375/1M	varies 5 cited scores	No measurements yet
OpenAI: GPT-5.5`openai/gpt-5.5`	4 routes	1,050,000	$5.275/1M	$31.65/1M	ZDR 3 cited scores	No measurements yet
Google: Gemini 3.5 Flash`google/gemini-3.5-flash`	3 routes	1,048,576	$1.5825/1M	$9.495/1M	ZDR	No measurements yet
MoonshotAI: Kimi K2.7 Code`moonshotai/kimi-k2.7-code`	+11 19 routes	262,144	$0.692291/1M to $1.31875/1M	$3.4815/1M to $4.82135/1M	ZDR 5 cited scores	No measurements yet
Z.ai: GLM 5.2`z-ai/glm-5.2`	+28 48 routes	1,048,576	$0.3587/1M to $2.370374/1M	$1.5825/1M to $6.838973/1M	Confidential + ZDR 4 cited scores	No measurements yet
MiniMax: MiniMax M3`minimax/minimax-m3`	+13 25 routes	1,048,576	$0.24265/1M to $0.633/1M	$1.0128/1M to $2.532/1M	ZDR 4 cited scores	No measurements yet