WizardLM 2 8x22B

Microsoft

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. #moe

Try Now

Technical Specifications

Context Window

65,535 tokens

Max Output

8,000 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.62

Non-Reasoning Output

$0.62

Legacy

Made legacy on

Reason

Old MoE fine-tune; no longer maintained

Recommended Replacement

Qwen3.6 Plus