Mistral

Mistral: mistral-large-3-675b-instruct-2512:free

mistral-large-3-675b-instruct-2512:free
128K context262.1K outToolsVisionFilesCacheStructuredPrefill
Released Dec 1, 2025Updated Dec 1, 2025

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Mode chatTokenizer Mistral

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 262.1K 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
max_tokensAll providers-
presence_penaltyAll providers-
response_formatAll providers-
seedAll providers-
stopAll providers-
structured_outputsAll providers-
temperatureAll providers0.0645
tool_choiceAll providers-
toolsAll providers-
top_pAll providersNot sent by default

Frequently asked questions

Similar models