Open-weights orchestration preset from TrustedRouter. One API key routes across 3 models, with automatic failover.
No card required. Start with 1 million free tokens.
About TrustedRouter Liberty 4.0
TrustedRouter Liberty 4.0 is an open-weights orchestration preset published by TrustedRouter, with a 1,048,576-token context window. It routes across 3 models inside the attested prompt path.
- Model ID
trustedrouter/liberty-4.0- Publisher
- TrustedRouter
- Orchestration
- synth named preset
- Modes
- chat
- Billing
- Credits or your own provider key
Set it up with your agent
Paste this into Claude Code, Cursor or any coding agent.
Use TrustedRouter Liberty 4.0 through TrustedRouter in this project.
1. Read https://trustedrouter.com/llms.txt
2. Point the OpenAI-compatible client at
https://api.trustedrouter.com/v1 and read the key from
TRUSTEDROUTER_API_KEY.
3. Set the model to trustedrouter/liberty-4.0.
4. Run the tests, then show me the diff before committing.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.trustedrouter.com/v1",
api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
response = client.chat.completions.create(
model="trustedrouter/liberty-4.0",
messages=[{"role": "user", "content": "What is the capital of France?"}],
)
print(response.choices[0].message.content)
curl https://api.trustedrouter.com/v1/chat/completions \
-H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "trustedrouter/liberty-4.0",
"messages": [{"role": "user", "content": "What is the capital of France?"}]
}'
Models used by this orchestration
This TrustedRouter model is an orchestration preset. The gateway routes through the component models below inside the attested prompt path, using the preset's worker, advisor, judge, or synthesizer roles.
| Component | Publisher | Prompt | Cached input | Completion |
|---|---|---|---|---|
| nvidia/nemotron-3-ultra-550b-a55b open weights NVIDIA: Nemotron 3 Ultra |
NVIDIA | $0.5275/1M to $2.11/1M | $0.1055/1M to $0.1266/1M | $2.26825/1M to $10.55/1M |
| reflection/beam-1.0 open weights Beam |
reflection | $0.422/1M | $0.0422/1M | $1.266/1M |
| meta-models/muse-spark-open open weights Muse Spark Open |
meta-models | $1.31875/1M | $0.15825/1M | $4.48375/1M |
Questions
What model ID should I use for TrustedRouter Liberty 4.0?
Use trustedrouter/liberty-4.0 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Do you log my 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.
Which providers serve TrustedRouter Liberty 4.0?
TrustedRouter currently lists no Credits provider route for TrustedRouter Liberty 4.0. Provider availability and routing eligibility can change as catalog and health data update.
How much does TrustedRouter Liberty 4.0 cost through TrustedRouter?
TrustedRouter currently publishes no Credits provider route for TrustedRouter Liberty 4.0, so no public Credits price is available.
How do I require zero data retention for TrustedRouter Liberty 4.0?
Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.
Start building with TrustedRouter Liberty 4.0.
No card required. Start with 1 million free tokens.
