AI Rate CardEmbed 4 vs voyage-3-large: API price and specs
Embed 4 is 33% cheaper than voyage-3-large on input price.
Embed 4 has a 300% larger context than voyage-3-large.
| Field | Embed 4 | voyage-3-large |
|---|---|---|
| Lowest input, per 1M | $0.12 | $0.18 +50% |
| Median input, per 1M | $0.12 | $0.19 +58.3% |
| Lowest output, per 1M | — | $0.20 |
| Median output, per 1M | — | $0.20 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | — | $0.22 |
| Context | 128K | 32K +75% |
| Max output | 2K | — |
| Providers | 4 | 3 +25% |
| Regions | US | — |
| Accepts | image, text | text |
| Returns | embeddings, text | embeddings, text |
| Type | Embeddings | Embeddings |
| Free option | no | no |
| Cheapest provider | aihubmix | vercel |
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, Embed 4 or voyage-3-large?
Embed 4 is 33% cheaper than voyage-3-large on input price.
Which has the larger context, Embed 4 or voyage-3-large?
Embed 4: 128K tokens; voyage-3-large: 32K tokens.
Where can I use both Embed 4 and voyage-3-large?
trustedrouter, vercel