---
id: "runinfra"
gateways: ["vercel"]
models: 12
endpoints: 12
tokens_week: 0
token_share: "0.0%"
rank: 129
cheapest_on: "4 of 11 shared models"
cheaper_than: "83% of offers at the median"
uptime_1d: 69.7000
latency_p50_ms: 470
tokens_per_second: 125
trains_on_some: true
retains_on_some: true
---
# runinfra

`alibaba/qwen3.8-2.4t-a95b`, `alibaba/qwen3.8-27b`, `alibaba/qwen3.8-flash-next`, `alibaba/qwen3-embedding-0.6b`, `alibaba/qwen3-embedding-8b`, `deepseek/deepseek-v4.1-flash`, `deepseek/deepseek-v4.1-flash-1017`, `deepseek/deepseek-v4-flash-0731`, `deepseek/deepseek-v4-pro-0813`, `nvidia/nemotron-3.5-lightning`, `zai/glm-5.3`, `zai/glm-5.3-flash`