---
id: "mistralai/ministral-8b"
also: ["mistralai/ministral-8b", "vercel/mistral/ministral-8b"]
card_usd_per_m: "0.11 in, 0.11 out, at mistral/us"
cheapest_list_usd_per_m: "0.11 in, 0.11 out, at mistral/us on openrouter"
cheapest_effective_usd_per_m: "0.1095 in, 0.1014 out, at mistral/us on openrouter"
context: 128000
max_output: 102400
input: ["text"]
output: ["text"]
released: "2024-10-17"
params: ["frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p"]
endpoints: 3
gateways: "openrouter (2), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# Mistral: Ministral 8B

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...