VQV Signal
According to a post on X by @OpenRouter, Particle has released Particle-1, a coding model post-trained on DeepSeek V4.1 Flash. Particle says the model uses 28 to 52 percent fewer output tokens than its base model across four coding benchmarks. The model is now available on OpenRouter and Vercel's AI Gateway. Merge says Particle already serves a big share of its Merge Gateway traffic.
According to a post on X by @OpenRouter, Particle has released Particle-1, a coding model post-trained on DeepSeek V4.1 Flash. Particle says the model uses 28 to 52 percent fewer output tokens than its base model across four coding benchmarks. The model is now available on OpenRouter and Vercel's AI Gateway. Merge says Particle already serves a big share of its Merge Gateway traffic.
AI-assisted summary based on the listed source.
Particle-1, post-trained on DeepSeek V4.1 Flash, uses 28 to 52 percent fewer output tokens than its base model across four coding benchmarks, according to Particle. It's now on OpenRouter and Vercel's AI Gateway, and Merge says Particle already serves a big share of its Merge Gateway traffic. Also:...
Teams whose costs depend on output token volume may find the model worth testing, though the efficiency figures come from Particle's own benchmarks. Developers can try it directly through OpenRouter or Vercel's AI Gateway. Next, watch for independent benchmark results and any more specific traffic figures from Merge.
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
VQV surfaced this signal because it is recent, relevant to AI Chips, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.
