Mistral Embed
Mistral Embed is Mistral's general-purpose text embedding model with 1024 dimensions, designed for semantic search and retrieval tasks with a 55.26 score on the MTEB benchmark.
- Input price
- Input $0.10, Per 1M tokens
import { embed } from 'ai';
const result = await embed({ model: 'mistral/mistral-embed', value: 'Sunny day at the beach',})Copy link to headingMore models by Mistral
| Model |
|---|
| 256K | 0.4 s | 87 tps | $0.50/M | $1.50/M | — |  | 12/02/2025 | |||||||
| 256K | 0.3 s | 127 tps | $0.20/M | $0.20/M | — | | 12/02/2025 | |||||||
| — | $0.15/M | — | | 05/28/2025 | ||||||||||
| 128K | 0.3 s | 175 tps | $0.10/M | $0.10/M | — | | 10/16/2024 | |||||||
| 32K | 0.3 s | 192 tps | $0.10/M | $0.30/M | — | | 09/17/2024 | |||||||
| 131K | 0.3 s | 87 tps | $0.15/M | $0.15/M | — |   | 07/18/2024 |