Ministral 8B Check detailed information and pricing for AI models

Context Length 128,000 tokens, mistralai from provided

128,000
Context Tokens
$0.10
Prompt Price
$0.10
Output Price
6/16
Feature Support

Model Overview

Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.

Basic Information

Developer
mistralai
Model Series
Mistral
Release Date
2024-10-17
Context Length
128,000 tokens
Variant
standard

Pricing Information

Prompt Tokens
$0.10 / 1M tokens
Completion Tokens
$0.10 / 1M tokens

Supported Features

Supported (6)

Seed
Frequency Penalty
Presence Penalty
Response Format
Tool Usage
Structured Outputs

Unsupported (10)

Image Input
Top K
Repetition Penalty
Min P
Logit Bias
Logprobs
Top Logprobs
Reasoning
Web Search Options
Top A

Actual Usage Statistics

#94
Out of 345 total models
4.8B
Total Tokens Last 30 Days
161.58M
Daily Average Usage
11%
Weekly Usage Change

Usage Trend for the Last 30 Days

Models by Same Author (mistralai)

Magistral Small 2506
40,000 tokens
$0.50 / $1.50
Magistral Medium 2506
40,960 tokens
$2.00 / $5.00
Magistral Medium 2506 (thinking)
40,960 tokens
$2.00 / $5.00
Devstral Small (free)
131,072 tokens
Free
Devstral Small
128,000 tokens
$0.06 / $0.12

Similar Price Range Models

Phi-3.5 Mini 128K Instruct
microsoft
128,000 tokens
$0.10 / $0.10
Phi-3 Mini 128K Instruct
microsoft
128,000 tokens
$0.10 / $0.10
Pixtral 12B
mistralai
32,768 tokens
$0.10 / $0.10