WizardLM-2 8x22B

64K context

Description

The WizardLM-2 8x22B is a state-of-the-art large language model, demonstrating highly competitive performance in complex chat, multilingual, reasoning, and agent tasks.

Pricing

  • Dedicated Endpoints: Calculated by the instance type and the number of GPUs, you can find the details in pricing page. You can also contact us to reserve GPUs.
  • Serverless Endpoints: $1 / M tokens for using WizardLM-2 8x22B, pay as you go.

Playground

System prompt
Temperature
Max tokens
Top P

API Reference

Lepton AI

© 2025