AI Rate CardGemma 3 4B IT vs nemotron-4-340b-instruct: API price and specs
Gemma 3 4B IT is 99% cheaper than nemotron-4-340b-instruct on input price.
Gemma 3 4B IT is 99% cheaper than nemotron-4-340b-instruct on output price.
Gemma 3 4B IT is 99% cheaper than nemotron-4-340b-instruct on a 1M-in / 200k-out workload.
Gemma 3 4B IT has a 3100% larger context than nemotron-4-340b-instruct.
| Field | Gemma 3 4B IT | nemotron-4-340b-instruct |
|---|---|---|
| Lowest input, per 1M | $0.04 | $4.20 +10400% |
| Median input, per 1M | $0.05 | $4.20 +8300% |
| Lowest output, per 1M | $0.05 | $4.20 +8300% |
| Median output, per 1M | $0.10 | $4.20 +4100% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.05 | $5.04 +9980% |
| Context | 131K | 4K +96.9% |
| Max output | 131K | — |
| Providers | 11 | 2 +81.8% |
| 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 | deepinfra |
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
Frequently asked questions
Which is cheaper, Gemma 3 4B IT or nemotron-4-340b-instruct?
Gemma 3 4B IT is 99% cheaper than nemotron-4-340b-instruct on input price. Gemma 3 4B IT is 99% cheaper than nemotron-4-340b-instruct on output price. Gemma 3 4B IT is 99% cheaper than nemotron-4-340b-instruct on a 1M-in / 200k-out workload.
Which has the larger context, Gemma 3 4B IT or nemotron-4-340b-instruct?
Gemma 3 4B IT: 131K tokens; nemotron-4-340b-instruct: 4K tokens.
Where can I use both Gemma 3 4B IT and nemotron-4-340b-instruct?
deepinfra, nvidia