OpenAI compatible API · Attested · Public status

OpenAI-Compatible LLM API Router

Keep the OpenAI SDK. Change base_url once and call hundreds of models through one API. Create a key and make the first request without a card.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Make your first API call

Keep the SDK. Change the base URL.

Use the OpenAI client you already have. Change base_url, create one key, and call hundreds of models through the same interface.

  • ✓ Install the standard openai package
  • ✓ Point it at https://api.trustedrouter.com/v1
  • ✓ Start with trustedrouter/cheap or choose any model ID

No card required. Your existing OpenAI SDK keeps working.

OpenAI SDK
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["TRUSTEDROUTER_API_KEY"],
    base_url="https://api.trustedrouter.com/v1",
)

response = client.chat.completions.create(
    model="trustedrouter/cheap",
    messages=[{"role": "user", "content": "Reply with PONG"}],
)

print(response.choices[0].message.content)

Measured providers

Use live TTFT, throughput, and uptime data instead of vendor claims.

Open leaderboard

Policy-aware routing

Compare ZDR, confidential compute, provider E2EE, and upstream policy sources.

Open providers

Verify the gateway

Check the running image, source commit, digest, and attestation path.

Open trust
Make the first call with your existing SDK. Create one key, copy the quickstart, and get a real model response.
No card required.
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.

556public models
92providers
1714configured routes
279ZDR routes
46provider E2EE routes
4024recent availability samples
Model Providers Context Input Output Privacy Measured route
Anthropic: Claude Opus 4.8anthropic/claude-opus-4.8
3 routes
1,000,000 $5.275/1M $26.375/1M varies 5 cited scores 1718 ms TTFT anthropic · 87 tok/s · 100.00% available · n=5
OpenAI: GPT-5.5openai/gpt-5.5
4 routes
1,050,000 $5.275/1M $31.65/1M ZDR 3 cited scores 1971 ms TTFT atlas-cloud · 100.00% available · n=2
Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash
+1
7 routes
1,048,576 $1.5825/1M $9.495/1M ZDR 1172 ms TTFT google-ai-studio · 100.00% available · n=4
MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code
+10
19 routes
262,144 $0.70685/1M to $1.00225/1M $3.587/1M to $4.22/1M ZDR 5 cited scores 1700 ms TTFT kimi · 30 tok/s · 100.00% available · n=31
Z.ai: GLM 5.2z-ai/glm-5.2
+27
48 routes
1,048,576 $0.7174/1M to $2.317369/1M $1.5825/1M to $7.080849/1M E2EE 4 cited scores 3822 ms TTFT arcee · 32 tok/s · 100.00% available · n=79
MiniMax: MiniMax M3minimax/minimax-m3
+10
22 routes
524,288 $0.24265/1M to $2.11/1M $1.0128/1M to $10.55/1M ZDR 4 cited scores measured together · 84 tok/s · 100.00% available · n=31
AnthropicPolicy varies 11 models 1803 ms p50 · n=60
GMI CloudPolicy varies 72 models 3854 ms p50 · n=27
OpenAIZDR on prepaid 45 models 1594 ms p50 · n=100
Atlas CloudPolicy varies 77 models 1971 ms p50 · n=7
Google AI StudioPolicy varies 13 models 1052 ms p50 · n=80
Google Vertex AIZDR on prepaid 11 models 1412 ms p50 · n=28
Lightning AIPolicy varies 35 models 1452 ms p50 · n=21
KimiPolicy varies 4 models 4224 ms p50 · n=135

Browse every modelReview provider policiesOpen the full leaderboardSnapshot 2026-09-09T00:03:39.830Z

Questions

Can I keep using the OpenAI SDK?

Yes. Set base_url to the TrustedRouter API and keep the usual chat completions or Responses API calls.

Can I still choose exact providers?

Yes. Use explicit model IDs, provider filters, or TrustedRouter aliases such as trustedrouter/auto and trustedrouter/zdr.

Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.