Open source, down to the deploy
Gateway, SDKs and deployment configuration are public. Attestation ties that source to the code serving requests.
- Read the source
- Check the attestation
- Match the digest to a commit
- Verify it fails closed
- Secure
- Smart
- Scalable
- Savings
Encrypt all your
AI chats
Access hundreds of models confidentially through a single OpenAI-compatible API.
No card required. Start with 1 million free tokens.
672 models. Every route labeled.
Featured · 6 of 672
| Model | Routes | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
 Z.ai: GLM 5.3 Flash z-ai/glm-5.3-flash |
from $0.07385 | from $0.2532 | 1.05M | |
Z.ai: GLM 5.3 z-ai/glm-5.3 |
from $0.1477 | from $3.20087 | 1.05M | |
 MoonshotAI: Kimi K3 moonshotai/kimi-k3 |
from $1.61415 | from $10.0225 | 1.05M | |
 DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 |
$1.3926 | $4.1778 | 1.05M | |
DeepSeek: DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 |
from $0.0422 | from $0.09495 | 1.05M | |
 MiniMax: MiniMax M3 minimax/minimax-m3 |
from $0.24265 | from $1.0128 | 1.05M | |
 OpenAI: GPT-6.1 Sol openai/gpt-6.1-sol |
$2.11 | $10.55 | 1.05M | |
DeepSeek: DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash |
from $0.0422 | from $0.0844 | 1.05M | |
MoonshotAI: Kimi K3 moonshotai/kimi-k3 |
from $1.61415 | from $10.0225 | 1.05M | |
 Google: Gemini 3.8 Flash google/gemini-3.8-flash |
$0.79125 | $3.95625 | 1.05M | |
MiniMax: MiniMax M3 minimax/minimax-m3 |
from $0.24265 | from $1.0128 | 1.05M | |
Z.ai: GLM 5.3 z-ai/glm-5.3 |
from $0.1477 | from $3.20087 | 1.05M | |
OpenAI: gpt-oss-120b openai/gpt-oss-120b |
from $0.03165 | from $0.17935 | 131K | |
DeepSeek: DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash |
from $0.0422 | from $0.0844 | 1.05M | |
MoonshotAI: Kimi K3 moonshotai/kimi-k3 |
from $1.61415 | from $10.0225 | 1.05M | |
Google: Gemma 4 31B google/gemma-4-31b-it |
from $0.09495 | from $0.3587 | 262K | |
Z.ai: GLM 5.3 z-ai/glm-5.3 |
from $0.1477 | from $3.20087 | 1.05M | |
 Qwen: Qwen3.6 27B qwen/qwen3.6-27b |
from $0.15825 | from $1.42425 | 262K |
Or choose a routing promisetrustedrouter/
Customer prices per 1M tokens. “From” is the lowest-priced route. Privacy varies by route.
Move over with one base_url change.
Keep your existing OpenAI-shaped calls. Add privacy and routing constraints only when you need them.
Base URL
https://api.trustedrouter.com/v1View code examples
from openai import OpenAI import os client = OpenAI( - base_url="https://api.openai.com/v1",- api_key=os.environ["OPENAI_API_KEY"],+ base_url="https://api.trustedrouter.com/v1",+ api_key=os.environ["TRUSTEDROUTER_API_KEY"], ) response = client.chat.completions.create( model="z-ai/glm-5.3-flash", messages=[{"role": "user", "content": "Hello"}], # optional: extra_body={"provider": {"min_privacy": "confidential"}} )
Your request.
Your rules.
Use the models you need through one API. Control which providers handle your requests and the privacy standards they must meet.
Explore routing controls-
Your app
Chat APIWhat is the capital of France?
-
TrustedRouter gateway
✓ Attested -
DeepSeek
✓ Served -
Response · 200
$0.000022The capital of France is Paris.
Don't trust. Verify.
An attested prompt path
Prompts travel through a gateway whose build is attested, kept apart from the dashboard and billing systems.
Open live trust evidenceThree clouds, visible fallback
Provider and model health are measured continuously, with public latency and availability history.
View public statusFails closed, never quietly downgrades
If no route meets your privacy minimum, the request stops before inference instead of falling back to a weaker one.
Read the privacy controlsSee what your AI bill is made of.
5.5%fee on provider costs
No monthly planNo seat fees
Bring your own keysUse your provider accounts
Flexible paymentsCard, ACH, PayPal or cryptocurrency
Strict budgets count requests still running toward daily, weekly or monthly limits per key.
Customer story · Robot, Robot & Human
170,974 legal documents.
Billions of routed tokens. Production in three weeks.
Customer perspective
RRH uses one OpenAI-compatible API for extraction, retrieval preparation and multi-stage legal reasoning, while every request crosses TrustedRouter's attested gateway.
“We handle other people's privileged litigation documents, the kind of material that gets subpoenaed. ‘Trust us, we won't peek’ was never an acceptable answer to give a client.”
Featured in · Axios
“In a demo, I was able to use a DeepSeek model in under 30 seconds using TrustedRouter, an open-source routing company.”
Read the storyWhat developers ask before routing.
What is TrustedRouter?
A privacy-first AI gateway that routes requests across many providers through one OpenAI-compatible API without logging prompt or output content.
Is this an OpenRouter alternative?
Yes, with an attested prompt path, public source, explicit privacy aliases, and fail-closed behavior as core design constraints.
Do you log prompts or outputs?
No. Prompt and output content are intentionally excluded from the control plane and metadata systems. Optional content export requires explicit destination-level configuration.
What does attested gateway mean?
The gateway runs in a Trusted Execution Environment and publishes evidence that connects the running image to public source. You can verify that evidence on the trust page.
Can I bring my own provider keys?
Yes. BYOK lets you retain provider commitments or enterprise rate limits while using the TrustedRouter routing and trust boundary.
What happens if attestation fails?
The gateway fails closed. It does not silently route prompts through an unverified fallback.
How do I migrate?
Keep the OpenAI SDK, change the base URL, and use the same chat or Responses calls. The migration guide includes tested examples.