AI Rate Cardall-MiniLM-L6-v2 vs multi-qa-mpnet-base-dot-v1: API price and specs
| Field | all-MiniLM-L6-v2 | multi-qa-mpnet-base-dot-v1 |
|---|---|---|
| Lowest input, per 1M | $0.005 | $0.005 |
| Median input, per 1M | $0.007 | $0.007 |
| Lowest output, per 1M | — | — |
| Median output, per 1M | — | — |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | — | — |
| Context | 512 | 512 |
| Max output | 384 +50% | 768 |
| Providers | 2 | 2 |
| Regions | — | — |
| Accepts | text | text |
| Returns | text | text |
| Type | Embeddings | Embeddings |
| Free option | no | no |
| Cheapest provider | deepinfra | 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 has the larger context, all-MiniLM-L6-v2 or multi-qa-mpnet-base-dot-v1?
all-MiniLM-L6-v2: 512 tokens; multi-qa-mpnet-base-dot-v1: 512 tokens.
Where can I use both all-MiniLM-L6-v2 and multi-qa-mpnet-base-dot-v1?
deepinfra, digitalocean