OpenAI compatible API. Attested gateway. Public status.
Llama 3.3 70B FP8 API
OpenAI compatible quickstart for Llama 3.3 70B FP8 on TrustedRouter.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
amd/llama-3.3-70b-instruct-fp8-kv
open weights
API
Use the same OpenAI compatible clients you already use. Only the base URL and model change.
from openai import OpenAI
client = OpenAI(
base_url="https://api.trustedrouter.com/v1",
api_key="sk-tr-v1-..."
)
response = client.chat.completions.create(
model="amd/llama-3.3-70b-instruct-fp8-kv",
messages=[{"role": "user", "content": "Give me a one-sentence status."}],
max_tokens=64,
)
print(response.choices[0].message.content)Endpoint metadata: https://api.trustedrouter.com/v1/models/amd/llama-3.3-70b-instruct-fp8-kv/endpoints