Ministral 8B
Ministral 8B brings an interleaved sliding-window attention architecture to edge inference, delivering faster and more memory-efficient processing across its full context window of 128K tokens at $0.15 per million tokens.
Tool Use
index.ts
import { streamText } from 'ai'
const result = streamText({ model: 'mistral/ministral-8b', prompt: 'Why is the sky blue?'})More models by Mistral AI
| Model |
|---|
| 256K | 0.4s | 60tps | $0.50/M | $1.50/M | — | — |  | 12/02/2025 | |||||
| 128K | 0.3s | 198tps | $0.10/M | $0.10/M | — | — | | 10/01/2024 | |||||
| 32K | 0.4s | 59tps | $0.10/M | $0.30/M | — | — | | 09/01/2024 | |||||
| 128K | 0.3s | 157tps | $0.30/M | $0.90/M | — | — | | 05/29/2024 | |||||
| $0.10/M | — | — | | 12/11/2023 | |||||||||
| 256K | 0.3s | 73tps | $1.50/M | $7.50/M | — | — | |