---
id: "sail"
gateways: ["requesty"]
models: 5
endpoints: 5
tokens_week: 0
token_share: "0.0%"
rank: 149
cheapest_on: "1 of 3 shared models"
cheaper_than: "90% of offers at the median"
latency_p50_ms: 4375
tokens_per_second: 81
trains_on_some: false
retains_on_some: false
quantization: "fp8 (1), mxfp4 (1), nvfp4 (1)"
---
# sail

`deepseek/deepseek-v4-flash-0731`, `google/gemma-4-31b`, `moonshotai/kimi-k2.6`, `openai/gpt-oss-120b`, `zai/glm-5.2`