Head to head
Gemini Embedding 2 vs Llama 3.1 8B Instant
On a blended workload of one million input tokens and three million output tokens, Gemini Embedding 2 is 1.4× cheaper than Llama 3.1 8B Instant.
| Gemini Embedding 2 | Llama 3.1 8B Instant | |
|---|---|---|
| Provider | Groq | |
| Input / MTok | $0.2 | $0.05 |
| Output / MTok | — | $0.08 |
| Cache read / MTok | — | — |
| Context window | — | 131,072 |
| Blended 1M in + 3M out | $0.20 | $0.29 |
| Status | ga | ga |