OpenAI compatible API · Attested · Public status

Meta: Llama 3.1 70B Instruct vs Tencent: Hy3

Compare Meta: Llama 3.1 70B Instruct and Tencent: Hy3 by providers, context, price, and TrustedRouter route support.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Compare routesProviders, price, context, and policy posture in one view.

Use auto when uptime mattersKeep a primary model and let fallback handle provider failures.

Same API shapeUse the OpenAI client and set the model you want.

Practical read

Tencent: Hy3 has the lower cheapest prompt+completion route on TrustedRouter. Tencent: Hy3 has more provider fallback routes, while Tencent: Hy3 has the larger context window. Probe-backed speed data is shown when enough recent samples exist.

$0.84/1MMeta: Llama 3.1 70B Instruct cheapest route

$0.693/1MTencent: Hy3 cheapest route

3008 msMeta: Llama 3.1 70B Instruct measured p50 TTFT

not enough dataTencent: Hy3 measured p50 TTFT

Meta: Llama 3.1 70B InstructTencent: Hy3

Model idmeta-llama/llama-3.1-70b-instructtencent/hy3

PublisherCerebrasDeepInfra

AI IQ — IQ 103#59

Context131,072 tokens262,144 tokens

Provider routes48

Cheapest route$0.84/1M$0.693/1M

Privacy postureprovider posture variesprovider posture varies

Modes chat chat

Meta: Llama 3.1 70B Instruct routes

Overview4 endpoints
PricingPrompt and completion rates
ProvidersAll serving providers

Tencent: Hy3 routes

Overview8 endpoints
PricingPrompt and completion rates
ProvidersAll serving providers

Production choice

Pick a default model. Keep fallback enabled.

TrustedRouter is useful when you know the model you want, but still need provider rollover, budget limits, usage records, and a prompt path you can verify.

OpenAI clientPython

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key="sk-tr-v1-..."
)

response = client.chat.completions.create(
    model="meta-llama/llama-3.1-70b-instruct",
    messages=messages,
)