AI Rate CardGemma-SEA-LION-v4-27B-IT vs nemotron-3-120b-a12b: API price and specs
Gemma-SEA-LION-v4-27B-IT is 60% cheaper than nemotron-3-120b-a12b on input price.
Gemma-SEA-LION-v4-27B-IT is 73% cheaper than nemotron-3-120b-a12b on output price.
Gemma-SEA-LION-v4-27B-IT is 65% cheaper than nemotron-3-120b-a12b on a 1M-in / 200k-out workload.
nemotron-3-120b-a12b has a 100% larger context than Gemma-SEA-LION-v4-27B-IT.
| Field | Gemma-SEA-LION-v4-27B-IT | nemotron-3-120b-a12b |
|---|---|---|
| Lowest input, per 1M | $0.20 | $0.50 +150% |
| Median input, per 1M | $0.35 | $0.51 +46.4% |
| Lowest output, per 1M | $0.40 | $1.50 +275% |
| Median output, per 1M | $0.56 | $1.54 +177.7% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.28 | $0.80 +185.7% |
| Context | 128K +50% | 256K |
| Max output | 128K | — |
| Providers | 4 | 2 +50% |
| Regions | GLOBAL | GLOBAL |
| Accepts | text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | huggingface | edenai |
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-SEA-LION-v4-27B-IT or nemotron-3-120b-a12b?
Gemma-SEA-LION-v4-27B-IT is 60% cheaper than nemotron-3-120b-a12b on input price. Gemma-SEA-LION-v4-27B-IT is 73% cheaper than nemotron-3-120b-a12b on output price. Gemma-SEA-LION-v4-27B-IT is 65% cheaper than nemotron-3-120b-a12b on a 1M-in / 200k-out workload.
Which has the larger context, Gemma-SEA-LION-v4-27B-IT or nemotron-3-120b-a12b?
Gemma-SEA-LION-v4-27B-IT: 128K tokens; nemotron-3-120b-a12b: 256K tokens.
Where can I use both Gemma-SEA-LION-v4-27B-IT and nemotron-3-120b-a12b?
edenai, trustedrouter