OpenAI compatible API · Attested · Public status

Qwen: Qwen3.6 35B A3B vs Tencent: Hy3

Compare Qwen: Qwen3.6 35B A3B and Tencent: Hy3 across token pricing, context windows, provider availability, privacy options, route diversity, and measured performance.

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

Qwen: Qwen3.6 35B A3B has the lower cheapest prompt+completion route on TrustedRouter. Qwen: Qwen3.6 35B A3B has more provider fallback routes, while Qwen: Qwen3.6 35B A3B has the larger context window. Current TrustedRouter probes show Qwen: Qwen3.6 35B A3B with the lower p50 TTFT.

$0.36225/1MQwen: Qwen3.6 35B A3B cheapest route

$0.693/1MTencent: Hy3 cheapest route

1828 msQwen: Qwen3.6 35B A3B measured p50 TTFT

2028 msTencent: Hy3 measured p50 TTFT

Qwen: Qwen3.6 35B A3BTencent: Hy3

Model idqwen/qwen3.6-35b-a3btencent/hy3

Publisher DeepInfra DeepInfra

AI IQ IQ 100#71 IQ 103#60

Context262,144 tokens262,144 tokens

Provider routes128

Cheapest route$0.36225/1M$0.693/1M

Privacy posturehas ZDR routeprovider posture varies

Modes chat chat

Qwen: Qwen3.6 35B A3B routes

Overview12 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="qwen/qwen3.6-35b-a3b",
    messages=messages,
)