WizardLM-2 8x22B

MicrosoftID: microsoft/wizardlm-2-8x22b

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is an instruct finetune of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). To read more about the model release, [click here](https://wizardlm.github.io/WizardLM2/). #moe

Pricing per 1M Tokens

Input (Prompt)$0.62
Output (Completion)$0.62
Cache ReadFree
Cache WriteFree
ImageN/A

Specifications

Context Length66K
Max Output Tokens8K
Input ModalitiesText
Output ModalitiesText
TokenizerMistral
Instruct Typevicuna
Top Provider Context66K
Top Provider Max Output8K
ModeratedNo

Compare this model

See how WizardLM-2 8x22B stacks up against other models.

vs Microsoft: Phi 4

More from Microsoft

Microsoft: Phi 4
Input$0.07
Context16K

Last updated: March 23, 2026

First tracked: March 23, 2026