---
id: "doubleword"
gateways: ["requesty"]
models: 12
endpoints: 12
tokens_week: 0
token_share: "0.0%"
rank: 130
cheapest_on: "0 of 9 shared models"
cheaper_than: "64% of offers at the median"
latency_p50_ms: 1529
tokens_per_second: 1440
trains_on_some: false
retains_on_some: true
---
# doubleword

`deepseek/deepseek-v4-flash`, `deepseek/deepseek-v4-flash-0424`, `deepseek/deepseek-v4-flash-0424:flex`, `deepseek/deepseek-v4-flash:flex`, `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-pro-0424`, `deepseek/deepseek-v4-pro-0424:flex`, `deepseek/deepseek-v4-pro:flex`, `nvidia/nvidia-nemotron-3-ultra`, `nvidia/nvidia-nemotron-3-ultra:flex`, `zai/glm-5.2`, `zai/glm-5.2:flex`