Particle-1 Launches with 28-52% Fewer Output Tokens
Particle API has launched Particle-1, a coding model post-trained on DeepSeek V4.1 Flash, claiming 28-52% fewer output tokens across four benchmarks compared to the base model. The model is now available on OpenRouter with pricing at $0.25/M input and $1/M output, supporting a 1.05M context window.
Full Report
OpenRouter · 2026-10-28 22
Fewer tokens, same work. Particle-1 from @particle_api uses 28–52% fewer output tokens than DeepSeek V4.1 Flash across four coding benchmarks, per Particle. Now on OpenRouter.
↳ 引用 @ModelsOnOR (Models on OpenRouter): Particle-1 from @particle_api is live on OpenRouter.
A token-efficient coding model post-trained on DeepSeek V4.1 Flash. Particle reports it uses ~45% fewer tokens on average with accuracy close to the base model, so agent tasks finish sooner and cost less.
1/M output, 1.05M context.