OpenRouter Alternative — TrustedRouter
An open-source, hardware-attested OpenRouter alternative. Same OpenAI-compatible API, verifiable prompt path, no logs.
An OpenRouter alternative built around verifiable privacy.
TrustedRouter is OpenAI-compatible, supports the same model catalog, and adds two things OpenRouter does not: hardware-attested execution and full open-source code.
You change one URL. Your existing code keeps working.
client = OpenAI(
base_url="https://api-azure.trustedrouter.com/v1",
api_key="sk-tr-v1-..."
)
# Same model IDs. Same SDK. Same code.
No prompt or output logs.
The attested gateway never persists request or response bodies. You can verify this by reading the open source.
Cryptographic, not contractual.
GCP Confidential Space signs the running image. The hosted prompt path is GCP-only and fails closed if attestation cannot be verified.
Every line that touches your prompt.
Control plane, gateway, configuration, web UI. Self-host if you want; the attestation story still works.
The teams switching over.
Privacy-sensitive workloads. Medical, legal, financial, internal tooling. Anywhere prompts shouldn't leave a hardware-attested boundary.
Regulated industries. HIPAA, FINRA, GDPR-strict deployments where "no logging" needs to be verifiable, not promised.
Audited routing. Build-vs-buy decisions where the security review team needs to read the routing code.
Self-hosters. Run TrustedRouter inside your own VPC and keep attestation working — your image hash is your image hash.
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 |
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 |
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 |
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 5.2z-ai/glm-5.2 |
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 M3minimax/minimax-m3 |
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 |
Browse every modelReview provider policiesOpen the full leaderboardSnapshot 2026-08-05T02:34:40Z