AI Rate CardGemma 3 4B IT vs Nemotron 3.5 Super VL 120B A12B: API price and specs
Gemma 3 4B IT is 62% cheaper than Nemotron 3.5 Super VL 120B A12B on input price.
Gemma 3 4B IT is 90% cheaper than Nemotron 3.5 Super VL 120B A12B on output price.
Gemma 3 4B IT is 76% cheaper than Nemotron 3.5 Super VL 120B A12B on a 1M-in / 200k-out workload.
| Field | Gemma 3 4B IT | Nemotron 3.5 Super VL 120B A12B |
|---|---|---|
| Lowest input, per 1M | $0.04 | $0.11 +163.8% |
| Median input, per 1M | $0.05 | $0.20 +300% |
| Lowest output, per 1M | $0.05 | $0.50 +900% |
| Median output, per 1M | $0.10 | $0.53 +427.5% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.05 | $0.21 +311% |
| Context | 131K | — |
| Max output | 131K | — |
| Providers | 11 | 3 +72.7% |
| Regions | EU, US | — |
| Accepts | image, image/gif, image/jpeg, image/png, image/webp, text | — |
| Returns | text | — |
| Type | Text models | Text models |
| Free option | yes | yes |
| Cheapest provider | amazon-bedrock | trustedrouter |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
huggingface, nvidia, trustedrouter
Frequently asked questions
Which is cheaper, Gemma 3 4B IT or Nemotron 3.5 Super VL 120B A12B?
Gemma 3 4B IT is 62% cheaper than Nemotron 3.5 Super VL 120B A12B on input price. Gemma 3 4B IT is 90% cheaper than Nemotron 3.5 Super VL 120B A12B on output price. Gemma 3 4B IT is 76% cheaper than Nemotron 3.5 Super VL 120B A12B on a 1M-in / 200k-out workload.
Where can I use both Gemma 3 4B IT and Nemotron 3.5 Super VL 120B A12B?
huggingface, nvidia, trustedrouter