Particle AI's token-efficient agentic coding model, post-trained on DeepSeek V4.1 Flash. 1M-token context for terminal workflows, codebase changes and data engineering, trained to finish them with far fewer reasoning and tool-call tokens while holding accuracy close to its base model.
▼Particle-1 is somewhat expensive at $0.05/M tokens input and $0.50/M tokens output. Cached input reads are priced at $0.003/M tokens, making repeated context cheaper. The model supports vision/image input, extended reasoning, a 1M context window.