Microsoft

WizardLM-2 8x22B

by Microsofttext->text1 endpoint

Overview

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...

Capabilities

Text generation
Structured output
Top-P sampling
Stop sequences
Deterministic seed

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
65.5K tokens
Max Output
8K tokens
Knowledge Cutoff
2024-04-30
Tokenizer
Mistral
Uptime (24h)
10000.0%

Supported Parameters

frequency_penaltymax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstoptemperaturetop_ktop_p

Pricing

Per 1M tokens
Input$0.62
Output$0.62
Added
April 16, 2024
Last synced 9/19/2026