---
id: "particle"
gateways: ["requesty", "vercel"]
models: 5
endpoints: 7
tokens_week: 0
token_share: "0.0%"
rank: 145
cheapest_on: "0 of 5 shared models"
cheaper_than: "70% of offers at the median"
uptime_1d: 99.7000
latency_p50_ms: 1170
tokens_per_second: 70
trains_on_some: false
retains_on_some: true
quantization: "fp8 (1)"
---
# particle

`deepseek/deepseek-v4.1-flash`, `deepseek/deepseek-v4.1-flash-1017`, `deepseek/deepseek-v4-flash-0731`, `particle/particle-1`, `zai/glm-5.3-flash`