---
id: "modelrun"
site: "modular.com"
headquarters: "US"
gateways: ["openrouter"]
models: 7
endpoints: 8
tokens_week: 90059549234
token_share: "0.6%"
rank: 31
cheapest_on: "0 of 8 shared models"
cheaper_than: "46% of offers at the median"
vs_card: "at the card price at the median over 6 models"
cache_hit: "85.4%"
uptime_1d: 97.2000
latency_p50_ms: 557
tokens_per_second: 140
trains_on_some: false
retains_on_some: false
quantization: "fp4 (7), fp8 (1)"
---
# ModelRun

`deepseek/deepseek-v4.1-flash-1017`, `google/gemma-4-31b-it`, `minimax/minimax-m3`, `minimax/minimax-m3.1-flash`, `moonshotai/kimi-k2.7-code`, `qwen/qwen3.8-27b`, `z-ai/glm-5.2`