OpenRouter (@OpenRouter)T1·68 pts
- Particle-1 reduces output token usage by 28-52% via post-training, targeting faster and cheaper agent task completion.
- Live on OpenRouter with a 1.05M context window and competitive pricing ($1/M output).
HOT RADAR
llmHEAT 22.2°
AI CURATED HOT STORY · 10/29/2026
Particle-1 Launches with 28-52% Fewer Output Tokens
1 reports archived1 independent sourcesupdated 10/29/2026, 06:01:25
Synthesis & Latest Updates
1 Sources Cross-ValidatedParticle 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.
LATEST/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.
Hourly heat curve
3 fully observed hoursNow
22.2
Peak
23.516:00
24h change
–
The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.