LLM
openrouter
vercel
nebius
amazon-bedrock
kenari
Nemotron Family
Open Source
Released: Mar 2026
Updated: Aug 2026 Nvidia Nemotron 3 Super 120B A12B
Nvidia Nemotron 3 Super 120B A12B is a LLM 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. Built on a hybrid Mamba-Transformer...
Vision
Audio
Tool Use
Reasoning
Citations
Key Specs
Context
1M
Max Output
262k
Best Price (Input / Output)
Chat with Model
$0.08 / $0.40 per 1M tokens
Pricing Comparison
| Provider | Input (1M) | Output (1M) | Image (1k) |
|---|---|---|---|
| kenari (Free Tier) | Free | Free | - |
| openrouter (Free Tier) | Free | Free | - |
| openrouter | $0.08 | $0.40 | - |
| amazon-bedrock | $0.15 | $0.65 | - |
| vercel | $0.15 | $0.65 | - |
| nebius | $0.30 | $0.90 | - |
Prices are per 1 million tokens unless otherwise noted. Image pricing is per 1000 images if applicable.
Price History
Prompt Price
Completion Price
Price trend per 1 million tokens over time.
Supported Parameters
frequency_penalty
reasoning
min_p
structured_outputs
response_format
include_reasoning
stop
top_k
max_tokens
top_logprobs
temperature
presence_penalty
tools
seed
tool_choice
logit_bias
reasoning_effort
logprobs
repetition_penalty
top_p