Nemotron 3 Super
by NVIDIA · nvidia/nemotron-3-super-120b-a12b · #53 cheapest of 325 paid models
Prices updated Jul 22, 2026, 2:19 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.08
per 1M tokens
Output
$0.45
per 1M tokens
Blended (3:1)
$0.172
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Nemotron 3 Super (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.172 | $0.00861 | — |
| 50% | $0.172 | $0.00861 | −0% |
| 90% | $0.172 | $0.00861 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000175 | $0.175 |
| Document summary | 8,000 | 1,000 | $0.00109 | $1.09 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0033 | $3.30 |
| Long-context analysis | 150,000 | 5,000 | $0.0143 | $14.25 |
Performance
Intelligence Index
25.4
AA composite quality
Coding Index
37.7
Math Index
—
Agentic Index
8.7
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Specs
Context window
1M
tokens
Max output
—
tokens
Input modalities
text
Tokenizer
Other