AI Rate Carddbrx-instruct vs gemma-2b: API price and specs
gemma-2b is 92% cheaper than dbrx-instruct on input price.
gemma-2b is 92% cheaper than dbrx-instruct on output price.
gemma-2b is 92% cheaper than dbrx-instruct on a 1M-in / 200k-out workload.
| Field | dbrx-instruct | gemma-2b |
|---|---|---|
| Lowest input, per 1M | $1.26 +1100% | $0.10 |
| Median input, per 1M | $1.26 +1100% | $0.10 |
| Lowest output, per 1M | $1.26 +1100% | $0.10 |
| Median output, per 1M | $1.26 +1100% | $0.10 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $1.51 +1100% | $0.13 |
| Context | — | — |
| Max output | — | — |
| Providers | 2 | 2 |
| Regions | — | — |
| Accepts | — | — |
| Returns | — | — |
| Type | Text models | Text models |
| Free option | yes | yes |
| Cheapest provider | aiml | aiml |
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, dbrx-instruct or gemma-2b?
gemma-2b is 92% cheaper than dbrx-instruct on input price. gemma-2b is 92% cheaper than dbrx-instruct on output price. gemma-2b is 92% cheaper than dbrx-instruct on a 1M-in / 200k-out workload.
Where can I use both dbrx-instruct and gemma-2b?
aiml, nvidia