Free to start

NVIDIA: Nemotron 3 Super vs Tencent: Hy3

Try both on us. Starter credit covers your first requests, then one key routes Nemotron 3 Super and Hy3. Switch by changing the model name.

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

Monthly evidence

NVIDIA: Nemotron 3 Super has the lower published input-plus-output rate and more Credits provider routes. Their context windows are the same size. There is not enough recent probe data to compare speed.

$0.511675/1MNVIDIA: Nemotron 3 Super cheapest route

$0.6963/1MTencent: Hy3 cheapest route

not enough dataNVIDIA: Nemotron 3 Super fastest measured p50 TTFT

2249 msTencent: Hy3 fastest measured p50 TTFT via tencent

The price comparison adds each route's rate for one million input tokens and one million output tokens; your cost depends on your input/output mix. Prices and live route measurements can change. Use the monthly reports when you need a stable evidence window, then run a small task-specific eval before choosing a production default.

NVIDIA: Nemotron 3 SuperTencent: Hy3

Model idnvidia/nemotron-3-super-120b-a12btencent/hy3

PublisherNVIDIA Tencent Cloud TokenHub

AI IQ — IQ 99#128

Context262,144 tokens262,144 tokens

Credits provider routes54

Cheapest route$0.511675/1M$0.6963/1M

Cached input$0.15825/1M$0.034815/1M to $0.05275/1M

Privacy posturehas ZDR routeprovider posture varies

Fastest measured p50 TTFTnot enough data2249 ms via tencent

Highest measured throughputnot enough datanot enough data

Recent route uptime range100.00%100.00%

Modes chat chat

NVIDIA: Nemotron 3 Super routes

Overview5 Credits routes
PricingInput, cached input, and output rates
ProvidersAll serving providers

Tencent: Hy3 routes

Overview4 Credits routes
PricingInput, cached input, and output rates
ProvidersAll serving providers

Related comparisons

Browse every comparison

NVIDIA: Nemotron 3 Super vs Z.ai: GLM 5.338 combined provider routes
NVIDIA: Nemotron 3 Super vs Z.ai: GLM 5.237 combined provider routes
NVIDIA: Nemotron 3 Super vs Z.ai: GLM 5.3 Flash37 combined provider routes
Tencent: Hy3 vs Z.ai: GLM 5.337 combined provider routes
Tencent: Hy3 vs Z.ai: GLM 5.236 combined provider routes
Tencent: Hy3 vs Z.ai: GLM 5.3 Flash36 combined provider routes
MoonshotAI: Kimi K3 vs NVIDIA: Nemotron 3 Super33 combined provider routes
MoonshotAI: Kimi K3 vs Tencent: Hy332 combined provider routes

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="nvidia/nemotron-3-super-120b-a12b",
    messages=messages,
)

Questions

Which should I use, NVIDIA: Nemotron 3 Super or Tencent: Hy3?

Is NVIDIA: Nemotron 3 Super or Tencent: Hy3 cheaper?

The current cheapest TrustedRouter route is $0.511675/1M for NVIDIA: Nemotron 3 Super and $0.6963/1M for Tencent: Hy3. The comparison uses current catalog prices and updates as provider pricing changes.

Is NVIDIA: Nemotron 3 Super or Tencent: Hy3 faster?

Current measured p50 time to first token is not enough data for NVIDIA: Nemotron 3 Super and 2249 ms for Tencent: Hy3. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test NVIDIA: Nemotron 3 Super and Tencent: Hy3 with the same API?

Yes. Use the same OpenAI-compatible TrustedRouter base URL and API key, then change only the model id between nvidia/nemotron-3-super-120b-a12b and tencent/hy3. This makes side-by-side evals possible without maintaining two provider integrations.