Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for huggingfaceh4

Zephyr 141B-A35B

huggingfaceh4/zephyr-orpo-141b-a35b

Model weights

Zephyr 141B-A35B is A Mixture of Experts (MoE) model with 141B total parameters and 35B active parameters. Fine-tuned on a mix of publicly available, synthetic datasets.

It is an instruct finetune of Mixtral 8x22B.

#moe

Modalities

Context

66K

Released

Apr 12, 2024

Knowledge Cutoff

Jan 2024

ActivityFAQExplore

Activity

Token volume and request traffic to this model over time.

Explore models like this

AI Model RankingsRanking

About Zephyr 141B-A35B

OpenRouter makes Zephyr 141B-A35B by Hugging Face H4 available through a unified, OpenAI-compatible API using the model ID huggingfaceh4/zephyr-orpo-141b-a35b.

Zephyr 141B-A35B accepts text and returns text. It has a 65,536-token context window.

It was released on April 12, 2024; its knowledge cutoff is January 31, 2024.

Frequently asked questions

Zephyr 141B-A35B is A Mixture of Experts (MoE) model with 141B total parameters and 35B active parameters. Fine-tuned on a mix of publicly available, synthetic datasets. It is an instruct finetune of Mixtral 8x22B. #moe

Zephyr 141B-A35B has a 65,536 token context window.

Zephyr 141B-A35B was released on April 12, 2024. Its knowledge cutoff is January 31, 2024.