Head to head
text-embedding-3-large vs Ministral 3 8B
On a blended workload of one million input tokens and three million output tokens, text-embedding-3-large is 4.6× cheaper than Ministral 3 8B.
| text-embedding-3-large | Ministral 3 8B | |
|---|---|---|
| Provider | OpenAI | Mistral |
| Input / MTok | $0.13 | $0.15 |
| Output / MTok | — | $0.15 |
| Cache read / MTok | — | — |
| Context window | — | — |
| Blended 1M in + 3M out | $0.13 | $0.60 |
| Status | ga | ga |