---
id: "runware"
gateways: ["requesty", "vercel"]
models: 12
endpoints: 20
tokens_week: 0
token_share: "0.0%"
rank: 110
cheapest_on: "5 of 18 shared models"
cheaper_than: "84% of offers at the median"
uptime_1d: 99.8000
latency_p50_ms: 1291
tokens_per_second: 123
trains_on_some: true
retains_on_some: true
quantization: "fp8 (2)"
---
# runware

`deepseek/deepseek-v4.1-flash`, `deepseek/deepseek-v4.1-flash-1017`, `deepseek/deepseek-v4-flash-0731`, `moonshotai/kimi-k3`, `moonshotai/kimi-k3.1-pro`, `moonshot/kimi-k3.1-pro`, `openai/gpt-oss-120b`, `qwen/qwen3.5-4b`, `qwen/qwen3.5-9b`, `zai/glm-5.2`, `zai/glm-5.3`, `zai/glm-5.3-flash`