Mistral: Mixtral 8x22B Instruct

flagship

Mistral · released 2024-04-10 · text->text

currently routing · 4.2k rpm

65K tokens

Context

$2.00 / 1M

Input

$6.00 / 1M

Output

— t/s

Speed

proprietary

License

/ ABOUT

Mixtral 8x22B Instruct is Mistral AI's open-weight Mixture-of-Experts model with 141B total parameters and 39B active per token, offering strong performance on diverse tasks.

Providers for Mistral: Mixtral 8x22B Instruct

1 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider

Context

Quant

Uptime · 30d

openrouter

65K

bf16

0.00%