Last updated: 16/04/2025

MistralOfficial Docs

Ministral 8B

ministral-8b-latest

active

Ministral 8B

Powerful edge model with an extremely high performance-to-price ratio, making it the world's best edge model for on-device use cases.

Supports a 131,072 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications. Supports tool use for advanced automation. Capable of generating structured output formats.

Additional Information

Notes

Context length of 131,072 tokens. Also available under the alias 'ministral-8b-2410'. Released under Mistral Research License.

Model Timeline

Launch Date

10/1/2024

Last Updated

10/1/2024

Capabilities

Text

Input Pricing

$0.10/ MTok

Context: 131,072 tokens

Output Pricing

$0.10/ MTok

Embeddings

Embeddings Pricing

$0.10/1k tokens

Additional Model Information

Tool Use

Yes

Structured Output

Yes

Reasoning

Yes

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop