Head to head

Gemini Embedding 001 vs Llama 3.1 8B Instant

On a blended workload of one million input tokens and three million output tokens, Gemini Embedding 001 is 1.9× cheaper than Llama 3.1 8B Instant.

Gemini Embedding 001Llama 3.1 8B Instant
Provider Google Groq
Input / MTok $0.15 $0.05
Output / MTok $0.08
Cache read / MTok
Context window 131,072
Blended 1M in + 3M out $0.15 $0.29
Status ga ga

Gemini Embedding 001 detail   Llama 3.1 8B Instant detail