Mixtral 8x7b

Description

The Mixtral 8x7b Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

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: $0.5 / M tokens for using Mixtral 8x7b, pay as you go.

Create a Dedicated Endpoint

Beyond the serverless endpoints, Lepton provides a simple way to create a dedicated endpoint for Mixtral 8x7b, which is a fully managed endpoint for your own use cases. If this model is what you are looking for, head over our dashboard to create your endpoint.