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.
LiteLLM lets you self-host. TrustedRouter lets you self-host and prove it.
LiteLLM is a great open-source proxy: one OpenAI-compatible API across 100+ models, runs in your own infra. The gap is verification — once it's deployed, nobody outside your ops team can confirm what the running proxy actually does with a prompt.
TrustedRouter closes that gap. The gateway runs in hardware enclaves and signs the exact binary it's running, so the no-logging guarantee is cryptographically checkable — by you, your auditors, or your customers.
client = OpenAI(
base_url="https://api.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.Run it in your own VPC.
Like LiteLLM, the full stack is open source and self-hostable. Unlike LiteLLM, the deployment is attestable end to end.
Prove the no-log claim.
Build the image, deploy to a confidential VM, and the attestation reports your hash. Your security team verifies instead of trusting your runbook.
Or skip the ops entirely.
Don't want to run a proxy? Use the hosted attested gateway at api.trustedrouter.com — same verification, zero infra.
When "trust our deployment" isn't enough.
If your security review, your customers, or your regulator needs evidence — not assurances — that prompts aren't logged, a self-hosted proxy alone doesn't get you there. Attestation does.
Read the full argument: “Attestation is All You Need”.
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.
| Model | Providers | Context | Input | Output | Privacy | Measured route |
|---|---|---|---|---|---|---|
Anthropic: Claude Opus 4.8anthropic/claude-opus-4.8 |
|
1,000,000 | $5.25/1M | $26.25/1M | varies 5 cited scores | 2886 ms TTFT anthropic · 58 tok/s · 100.00% available · n=5 |
OpenAI: GPT-5.5openai/gpt-5.5 |
|
1,050,000 | $5.25/1M | $31.5/1M | ZDR 3 cited scores | 2180 ms TTFT openai · 100.00% available · n=5 |
Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash |
+1
|
1,048,576 | $1.575/1M | $9.45/1M | ZDR | 1997 ms TTFT google-ai-studio · 100.00% available · n=17 |
MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code |
+8
|
262,144 | $0.735/1M to $0.9975/1M | $3.675/1M to $4.2/1M | ZDR 5 cited scores | 1618 ms TTFT inceptron · 100.00% available · n=42 |
Z.ai: GLM 5.2z-ai/glm-5.2 |
+22
|
1,048,576 | $0.714/1M to $1.575/1M | $1.575/1M to $5.5125/1M | E2EE 4 cited scores | 4152 ms TTFT parasail · 29 tok/s · 97.44% available · n=230 |
MiniMax: MiniMax M3minimax/minimax-m3 |
+8
|
1,048,576 | $0.2835/1M to $0.63/1M | $1.155/1M to $2.52/1M | ZDR 4 cited scores | 1785 ms TTFT minimax · 69 tok/s · 100.00% available · n=41 |
Browse every modelReview provider policiesOpen the full leaderboardSnapshot 2026-08-07T03:38:09Z