Megatron MarketsWholesale
Sign inContact Us
Models Model details

Mistral AI

Mistral: Mixtral 8x22B Instruct

mistralai/mixtral-8x22b-instruct

Enquire about this model Request a quote

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding, and reasoning - large context length (64k) - fluency in English, French, Italian, German, and Spanish See benchmarks on the launch announcement here. #moe

Input
$2

/ 1M tokens

Output
$6

/ 1M tokens

Context window
65.54K

tokens

Limits

Context

65,536

tokens

Max output

52,428

80% of the context window

Parameters

140,630,071,296

Model facts

Author

Mistral AI

Tokenizer

Mistral

Modality

Text + File -> Text

Instruction format

Mistral

License

Apache-2.0

Knowledge cutoff

2024-01-31

Created

Apr 17, 2024

Hugging Face

mistralai/Mixtral-8x22B-Instruct-v0.1

Default generation parameters

temperature

0.3

Publication status

Hugging Face: verifiedLicense: publishedParameter count: published

Modalities

Input · TextInput · FileOutput · Text

Generation controls

Frequency penaltyMax tokensPresence penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop p

Capability scores

5.7
Intelligence index

Better than 3% of models compared