Mistral

Mistral: ministral-8b-2512:free

ministral-8b-2512:free
262.1K context262.1K outVisionCacheStructuredPrefill
Released Dec 2, 2025Updated Dec 2, 2025

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.

Mode chatTokenizer MistralQuantization fp8mistralai/Ministral-3-8B-Instruct-2512

All providers for this model are busy right now

Every upstream provider has hit its rate limit. The model comes back automatically once limits lift, usually within hours. Try again in a little while or switch to another model.

Request this model on Discord

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 128K tokensCompatible endpoints openaiVendor Mistral

Performance

Loading performance data...

Usage & Ranking

Loading usage...

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

ParameterProvidersDefault
frequency_penaltyAll providersNot sent by default
logprobsSome providers-
max_tokensAll providers-
presence_penaltyAll providers-
repetition_penaltySome providers-
response_formatAll providers-
seedAll providers-
stopAll providers-
structured_outputsAll providers-
temperatureAll providers0.3
tool_choiceAll providers-
toolsAll providers-
top_logprobsSome providers-
top_pAll providersNot sent by default

Frequently asked questions

Similar models