Particle-1
Token-efficient coding model post-trained on DeepSeek V4.1 Flash, using about 45% fewer tokens
particle.ai/blog/introducing-particle-1
Community-submitted · content unverified. This organization has not verified ownership or the information in this profile.
About
Particle-1 is Particle's first model, post-trained with reinforcement learning on DeepSeek V4.1 Flash to complete software engineering and data engineering tasks with fewer reasoning and tool-call tokens while keeping accuracy close to the base model. It has a 1M-token context window, supports tool calling and structured outputs, and is available via Particle's API, Vercel AI Gateway and OpenRouter.
- Added via
- web
- Ownership
- unclaimed
Where to go
For people
- Homepageparticle.ai/blog/introducing-particle-1
For agents
Nothing listed yet.
Product details
- Product kind
- Api