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$0.30 / $2.40
Context1M
ReleasedMar 11, 2026

Providers

3 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
DeepInfraus · bf16$0.09$0.40Variable7.09s60 tps100%
Crusoefp8$0.30$2.40$0.150.32s138 tps100%
DekaLLMfp8$0.08$0.45Variable1.20s44 tps99.77%

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
$0.30
per 1M tokens
Output
$2.40
per 1M tokens
Cache read
$0.15
per 1M cached tokens
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.

0.0s2.5s5.0s7.5s10.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
Crusoe DeepInfra (us) DekaLLM
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
Crusoe DeepInfra (us) DekaLLM

Uptime

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

Last 3 daysAvailability 99.75%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.9%
100% 98% 97% 95%
Oct 31, 6:10 PMNow

Apps

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

Hermes AgentPersonal Agent · 87.2% of tokens13.7BOpenHandsCli Agent · 6.5% of tokens1.0BPortkey AIProgramming App · 2.5% of tokens392.5MOpenClawPersonal Agent · 2% of tokens313.9MpiCli Agent · 1.8% of tokens286.8M

Activity

45.9B tokens processed market-wide in the last month.

01.0B2.0B3.0B4.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
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 https://minuykh.app/v1.
How much context does Nemotron 3 Super hold?
1,048,576 tokens per request, of which up to 262,144 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 $0.30 per 1M input tokens and $2.40 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