AI Rate CardBGE M3 vs all-MiniLM-L6-v2: API price and specs
all-MiniLM-L6-v2 is 50% cheaper than BGE M3 on input price.
BGE M3 has a 1500% larger context than all-MiniLM-L6-v2.
| Field | BGE M3 | all-MiniLM-L6-v2 |
|---|---|---|
| Lowest input, per 1M | $0.01 +100% | $0.005 |
| Median input, per 1M | $0.01025 +46.4% | $0.007 |
| Lowest output, per 1M | $0.01 | — |
| Median output, per 1M | $0.01025 | — |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.012 | — |
| Context | 8K | 512 +93.8% |
| Max output | — | 384 |
| Providers | 6 | 2 +66.7% |
| 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 is cheaper, BGE M3 or all-MiniLM-L6-v2?
all-MiniLM-L6-v2 is 50% cheaper than BGE M3 on input price.
Which has the larger context, BGE M3 or all-MiniLM-L6-v2?
BGE M3: 8K tokens; all-MiniLM-L6-v2: 512 tokens.
Where can I use both BGE M3 and all-MiniLM-L6-v2?
deepinfra, digitalocean