---
id: "particle-ai/particle-1"
also: ["particle-ai/particle-1-20261027", "requesty/particle/particle-1", "vercel/particle/particle-1"]
card_usd_per_m: "0.05 in, 0.5 out, at particle-ai/us"
cheapest_list_usd_per_m: "0.05 in, 0.5 out, at particle-ai/us on openrouter"
cheapest_effective_usd_per_m: "0.0109 in, 0.4998 out, at particle-ai/us on openrouter"
context: 1048576
max_output: 131072
input: ["text", "image"]
output: ["text"]
released: "2026-10-28"
reasoning: ["max", "xhigh", "high", "medium", "low", "minimal", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 3
gateways: "openrouter (1), requesty (1), vercel (1)"
no_training: 3
trains: 0
retains_prompts: 1
---
# Particle AI: Particle-1

Particle-1 is Particle AI's own frontier model, built for chat, agentic coding and tool calling workloads. It offers a 1M token context window, up to 131K output tokens, native image input and adjustable reasoning effort from none to max, with thinking on by default at high effort. Supports OpenAI style tools and tool\_choice, JSON object output and prompt caching.