AI Rate CardGemini Embedding 2 vs text-embedding-3-large: API price and specs
Gemini Embedding 2 is 34% cheaper than text-embedding-3-large on input price.
Gemini Embedding 2 is 34% cheaper than text-embedding-3-large on output price.
Gemini Embedding 2 is 34% cheaper than text-embedding-3-large on a 1M-in / 200k-out workload.
| Field | Gemini Embedding 2 | text-embedding-3-large |
|---|---|---|
| Lowest input, per 1M | $0.0686 | $0.10 +51.6% |
| Median input, per 1M | $0.20 +53.8% | $0.13 |
| Lowest output, per 1M | $0.0686 | $0.10 +51.6% |
| Median output, per 1M | $0.0686 | $0.12 +70.6% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.08232 | $0.12 +51.6% |
| Context | 8K | 8K |
| Max output | 1 +100% | 3K |
| Providers | 5 +44.4% | 9 |
| Regions | — | — |
| Accepts | audio, file, image, pdf, text, video | text |
| Returns | embedding, embeddings, text | embedding, embeddings, text, vector |
| Type | Embeddings | Embeddings |
| Free option | no | no |
| Cheapest provider | aihubmix | cometapi |
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
aihubmix, impossibl, vercel, zenmux
Frequently asked questions
Which is cheaper, Gemini Embedding 2 or text-embedding-3-large?
Gemini Embedding 2 is 34% cheaper than text-embedding-3-large on input price. Gemini Embedding 2 is 34% cheaper than text-embedding-3-large on output price. Gemini Embedding 2 is 34% cheaper than text-embedding-3-large on a 1M-in / 200k-out workload.
Which has the larger context, Gemini Embedding 2 or text-embedding-3-large?
Gemini Embedding 2: 8K tokens; text-embedding-3-large: 8K tokens.
Where can I use both Gemini Embedding 2 and text-embedding-3-large?
aihubmix, impossibl, vercel, zenmux