Search/
Skip to content
/

Qwen: Qwen3 4B

qwen/qwen3-4b

Released Apr 30, 2025Knowledge cutoff Mar 31, 2025128,000 context

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.

OpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Apps
  • Models
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Announcements
  • CareersHiring
  • Privacy
  • Terms of Service
  • Support
  • State of AI
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • SDK
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube

Recent activity on Qwen3 4B

Total usage per day on OpenRouter

Reasoning
81M
Prompt
33.7M
Completion
4.74M

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.