---
id: "modal"
site: "modal.com"
headquarters: "US"
gateways: ["openrouter", "vercel"]
models: 14
endpoints: 20
tokens_week: 73811032620
token_share: "0.5%"
rank: 36
cheapest_on: "5 of 20 shared models"
cheaper_than: "45% of offers at the median"
vs_card: "at the card price at the median over 7 models"
cache_hit: "88.6%"
uptime_1d: 99.8000
latency_p50_ms: 546
tokens_per_second: 112
trains_on_some: false
retains_on_some: false
quantization: "unknown (7), mxfp4 (2), fp4 (1), fp8 (1), nvfp4 (1)"
---
# Modal

`alibaba/qwen3.8-2.4t-a95b`, `deepseek/deepseek-v4.1-flash`, `deepseek/deepseek-v4.1-flash-1017`, `google/gemma-4-31b-it`, `meta/muse-spark-open`, `moonshotai/kimi-k3`, `moonshotai/kimi-k3.1-pro`, `qwen/qwen3.8-2.4t-a95b`, `qwen/qwen3.8-27b`, `thinkingmachines/inkling`, `z-ai/glm-5.3`, `zai/glm-5.3`, `z-ai/glm-5.3-flash`, `zai/glm-5.3-flash`