Start free trial

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b
CompareAPITry this model

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.

Modalities
In / out per 1M$0.08 / $0.45
Context256K
ReleasedMar 11, 2026

Providers

3 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Crusoefp8$0.30$2.40$0.150.40s139 tps100%
DekaLLMfp8$0.08$0.45Variable1.77s33 tps99.91%
DeepInfraus · bf16$0.09$0.40Variable7.12s68 tps99.91%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Nemotron 3 Super in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Nemotron 3 Super costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.08
per 1M tokens
Output
$0.45
per 1M tokens
Cache read
—
not published
Included in every pass
Nemotron 3 Super is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s5.0s10.0s15.0s20.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Crusoe DeepInfra (us) DekaLLM
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Crusoe DeepInfra (us) DekaLLM

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.56%
Oct 16, 11:00 AMNow
Availability over the last 24 hoursAvailability 99.72%
100% 98% 97% 95%
Oct 18, 11:00 AMNow

Apps

Tools that most often run Nemotron 3 Super, by tokens this week.

Hermes AgentPersonal Agent · 73.2% of tokens14.5BClaude CodeCli Agent · 21.2% of tokens4.2BPortkey AIProgramming App · 2% of tokens392.5MAI Web Translator Extension1.8% of tokens363.5MOpenClawPersonal Agent · 1.8% of tokens352.4M

Activity

46.8B tokens processed market-wide in the last month.

01.0B2.0B3.0B4.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens

FAQ

Which model id do I use for Nemotron 3 Super?
nvidia/nemotron-3-super-120b-a12b. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Nemotron 3 Super hold?
262,144 tokens per request, of which up to 235,929 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Nemotron 3 Super cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.08 per 1M input tokens and $0.45 per 1M output tokens.
Who built Nemotron 3 Super?
NVIDIA, in the Nemotron family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion