https://api.trustedrouter.eu
All requests require a valid Bearer token from your TrustedRouter account. Include it in the Authorization header.
Authorization: Bearer <your-trustedrouter-token>
| Method | Path | Description | Compat |
|---|---|---|---|
POST | /v1/chat/completions | Create a chat completion | OpenAI |
POST | /v1/completions | Create a text completion | OpenAI |
GET | /v1/models | List available models | OpenAI |
GET | /v1/models/{model} | Get model details | OpenAI |
POST | /v1/embeddings | Create embeddings | OpenAI |
POST | /api/generate | TGI generate endpoint | TGI |
POST | /api/chat | TGI chat endpoint | TGI |
GET | /api/info | Get TGI model info | TGI |
GET | /health | Health check | Internal |
GET | /metrics | Prometheus metrics | Internal |
| Header | Value | Description |
|---|---|---|
Authorization | Bearer <token> | TrustedRouter access token |
Content-Type | application/json | Required for all POST requests |
x-user-id | string | Optional user identifier for tracking |
from openai import OpenAI
client = OpenAI(
base_url="https://api.trustedrouter.eu/v1",
api_key="<your-trustedrouter-token>"
)
response = client.chat.completions.create(
model="tngtech/DeepSeek-TNG-R1T2-Chimera",
messages=[
{"role": "user", "content": "Hello, TrustedRouter!"}
]
)
print(response.choices[0].message.content)
curl https://api.trustedrouter.eu/v1/chat/completions \
-H "Authorization: Bearer <your-trustedrouter-token>" \
-H "Content-Type: application/json" \
-d '{
"model": "tngtech/DeepSeek-TNG-R1T2-Chimera",
"messages": [{"role": "user", "content": "Hello, TrustedRouter!"}]
}'
const response = await fetch(
"https://api.trustedrouter.eu/v1/chat/completions",
{
method: "POST",
headers: {
"Authorization": "Bearer <your-trustedrouter-token>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "tngtech/DeepSeek-TNG-R1T2-Chimera",
messages: [{ role: "user", content: "Hello, TrustedRouter!" }]
})
}
);
const data = await response.json();
console.log(data.choices[0].message.content);
Apply now for the first-user trial and be among the selected organisations shaping sovereign AI in Europe. Your access is granted within 24 hours.
We analyze your use cases, throughput needs, and compliance requirements to design the right capacity allocation.
TNG provisions dedicated GPU slices on our German infrastructure and configures your Keycloak tenant.
Switch to full sovereignty by exchanging the base URL and API token. If you need deeper integration or custom workflows, our consulting experts will guide you.
Run production-like workloads while we monitor, tune routing, and optimize model selection for your use case.
Scale to production with SLA guarantees, dedicated support channels, and ongoing performance optimization.