Suhail Doshi launches Particle to cut coding agents' token use

Suhail Doshi launched Particle on October 28 with Particle-1, a post-trained version of DeepSeek V4.1 Flash that the company says completed coding and data-engineering tasks using fewer output tokens than its base model across four software and data-engineering benchmarks. Particle offers Particle-1 through an API at the same per-token rates as DeepSeek V4.1 Flash, betting that lower token use on coding tasks can give it a durable API advantage. Doshi previously co-founded Mixpanel after interning at Slide and later founded the AI creative-tools company Playground.

Suhail Doshi launches Particle to cut coding agents' token use Particle-1 is a post-trained version of DeepSeek V4.1 Flash, available through an API; Particle says it used fewer tokens across four software and data-engineering benchmarks. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published Primary source: x.com https://x.com/Suhail/status/2115497949421883648 Why it matters Particle is selling efficiency gained through post-training while charging the same per-token rates as its base model. Its launch tests whether lower token use on coding tasks can give Particle a durable API advantage. Suhail Doshi https://x.com/Suhail launched Particle on October 28th with Particle-1, a developer-focused model that the company says completed coding and data-engineering tasks using fewer output tokens than its underlying model. Doshi saw the need for product-usage analytics while interning at Slide, then co-founded Mixpanel. He later founded Playground, an AI creative-tools company. Particle moves him into model training and inference infrastructure.… When you purchase through links in our articles, we may earn a small commission https://runtimewire.com/affiliate-monetization-standards . This doesn’t affect our editorial independence.