# Particle-1, a coding model that uses fewer tokens, lands on OpenRouter



OpenRouter



Particle-1, a coding model post-trained from DeepSeek V4.1 Flash, is now on OpenRouter. Particle says that across four coding benchmarks it uses 28–52% fewer output tokens than the base model \(about 45% on average\) with nearly the same accuracy. Pricing is $0.25 per million input tokens and $1 per million output, with a 1.05M-token context window.

- Announcement time: Oct 29, 2026 06:01 · Beijing Time (UTC+8)
- Review updated: Oct 29, 2026 10:33 Thu · Beijing Time (UTC+8)

## Sources

- Source excerpt: https://x.com/OpenRouter/status/2115564621717512295

Canonical entry: https://www.ailyre.com/source/?id=openrouter-particle-1-2026-10-28&lang=en