Mistral AItext->text

Mistral: Mixtral 8x22B Instruct

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](https://mistral.ai/news/mixtral-8x22b/). #moe

Context Window

66K

Input Price

$2.00/M tokens

Output Price

$6.00/M tokens

Modality

text->text

Pricing Breakdown

Cost per million tokens for input and output

Input$2.00/M tokens

Output$6.00/M tokens

Cost Example: Processing 10,000 input tokens and generating 1,000 output tokens would cost approximately $0.026000

Context Window Size

Maximum tokens the model can process in a single request

Context Window66K tokens

7% of 1M max

~49K

Words Equivalent

~33

Pages of Text

~655

Code Functions

Best Use Cases

What this model excels at

CodingProgrammingDevelopmentMathReasoningAnalysis

Related Categories:

Data Analysis

Test Mistral: Mixtral 8x22B Instruct Now

Compare this model with others using your own prompts

Ready to Test Mistral: Mixtral 8x22B Instruct?

Use our free AI Models Tester to compare Mistral: Mixtral 8x22B Instruct with other models side-by-side using your own prompts. See real results instantly.