Us Gov Nvidia Nemotron Super 3 120 B pricing
Source: litellm · updated 2026-10-28
Short answer: Us Gov Nvidia Nemotron Super 3 120 B costs $0.180 per million input tokens and $0.780 per million output tokens. That is a 3:1 blended rate of $0.330 per million tokens, ranking it #218 of 713 tracked models by input price.
Input / 1M
$0.180
Output / 1M
$0.780
Output ÷ input
4.33×
Context window
256,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.180 |
| Output, per 1M tokens | $0.780 |
| Output ÷ input multiple | 4.33× |
| 3:1 blended, per 1M tokens | $0.330 |
| Context window | 256,000 tokens |
| Vendor | us |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.180 | $0.195 | $0.375 |
| 10M in / 2.5M out | $1.80 | $1.95 | $3.75 |
| 100M in / 25M out | $18.00 | $19.50 | $37.50 |
Other us models
| Model | Input | Output |
|---|---|---|
| Us Gov Nvidia Nemotron Nano 3 30 B | $0.072 | $0.288 |
| Us Gov Nvidia Nemotron Nano 9 B | $0.072 | $0.276 |
| Us Gov Openai GPT OSS 20 B1.0 | $0.084 | $0.360 |
| Us Gov Anthropic Claude Haiku 5.5 | $0.120 | $0.600 |
| Us Gov Openai GPT OSS 120 B1.0 | $0.180 | $0.720 |
Compare against
- Us Gov Nvidia Nemotron Super 3 120 B vs Us Gov Openai GPT OSS 120 B1.0
- Us Gov Nvidia Nemotron Super 3 120 B vs Llama Guard 4 12 B
Cheaper alternatives
Next cheaper option: Morph GLM 53 Flash at $0.200 per 1M input tokens. Next step up: Qwen 3.8 27 B at $0.039 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.