OpenAI compatible API · Attested · Public status

NVIDIA: Nemotron 3 Super vs OpenAI: gpt-oss-20b

NVIDIA: Nemotron 3 Super vs gpt-oss-20b: compare current API pricing, context, provider routes, privacy, p50 latency, and OpenAI-compatible access.

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

Monthly evidence

OpenAI: gpt-oss-20b has the lower cheapest prompt+completion route on TrustedRouter. OpenAI: gpt-oss-20b has more provider fallback routes, while NVIDIA: Nemotron 3 Super has the larger context window. Probe-backed speed data is shown when enough recent samples exist.

$0.511675/1MNVIDIA: Nemotron 3 Super cheapest route

$0.1266/1MOpenAI: gpt-oss-20b cheapest route

not enough dataNVIDIA: Nemotron 3 Super fastest measured p50 TTFT

1018 msOpenAI: gpt-oss-20b fastest measured p50 TTFT via io-net

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 SuperOpenAI: gpt-oss-20b

Model idnvidia/nemotron-3-super-120b-a12bopenai/gpt-oss-20b

Publisher DeepInfra OpenAI

AI IQ — IQ 93#113

Context262,144 tokens131,072 tokens

Credits provider routes412

Cheapest route$0.511675/1M$0.1266/1M

Cached input$0.15825/1M$0.0211/1M to $0.033233/1M

Privacy posturehas ZDR routehas ZDR route

Fastest measured p50 TTFTnot enough data1018 ms via io-net

Highest measured throughputnot enough datanot enough data

Recent route uptime range100.00%75.00% to 100.00%

Modes chat chat

NVIDIA: Nemotron 3 Super routes

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

OpenAI: gpt-oss-20b routes

Overview12 Credits routes
PricingInput, cached input, and output rates
ProvidersAll serving providers

Related comparisons

Browse every comparison

OpenAI: gpt-oss-20b vs Z.ai: GLM 5.240 combined provider routes
OpenAI: gpt-oss-20b vs Z.ai: GLM 5.339 combined provider routes
OpenAI: gpt-oss-20b vs Z.ai: GLM 5.3 Flash38 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: gpt-oss-20b36 combined provider routes
MoonshotAI: Kimi K3 vs OpenAI: gpt-oss-20b36 combined provider routes
OpenAI: gpt-oss-120b vs OpenAI: gpt-oss-20b34 combined provider routes
MoonshotAI: Kimi K2.6 vs OpenAI: gpt-oss-20b32 combined provider routes
NVIDIA: Nemotron 3 Super vs Z.ai: GLM 5.232 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 OpenAI: gpt-oss-20b?

Is NVIDIA: Nemotron 3 Super or OpenAI: gpt-oss-20b cheaper?

The current cheapest TrustedRouter route is $0.511675/1M for NVIDIA: Nemotron 3 Super and $0.1266/1M for OpenAI: gpt-oss-20b. The comparison uses current catalog prices and updates as provider pricing changes.

Is NVIDIA: Nemotron 3 Super or OpenAI: gpt-oss-20b faster?

Current measured p50 time to first token is not enough data for NVIDIA: Nemotron 3 Super and 1018 ms for OpenAI: gpt-oss-20b. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test NVIDIA: Nemotron 3 Super and OpenAI: gpt-oss-20b 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 openai/gpt-oss-20b. This makes side-by-side evals possible without maintaining two provider integrations.