---
id: "microsoft/wizardlm-2-8x22b"
also: ["microsoft/wizardlm-2-8x22b", "microsoft/WizardLM-2-8x22B", "hf/alpindale/WizardLM-2-8x22B", "requesty/microsoft/wizardlm-2-8x22b"]
cheapest_list_usd_per_m: "0.62 in, 0.62 out, at novita on hf"
cheapest_effective_usd_per_m: "0.6199 in, 0.6173 out, at novita/bf16 on openrouter"
context: 65535
max_output: 8000
input: ["text"]
output: ["text"]
released: "2024-04-16"
params: ["frequency_penalty", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "temperature", "top_k", "top_p"]
endpoints: 3
gateways: "hf (1), openrouter (1), requesty (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# 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...