---
id: "sference"
gateways: ["requesty"]
models: 9
endpoints: 9
tokens_week: 0
token_share: "0.0%"
rank: 139
cheapest_on: "2 of 8 shared models"
cheaper_than: "20% of offers at the median"
latency_p50_ms: 515
tokens_per_second: 180
trains_on_some: false
retains_on_some: false
quantization: "fp4 (6)"
---
# sference

`cloudflare/clef`, `deepseek/deepseek-v4.1-flash`, `deepseek/deepseek-v4.1-flash-1017`, `deepseek/deepseek-v4-flash-0731`, `moonshot/kimi-k3`, `sference/thinkingcap-qwen3.6-27b`, `zai/glm-5.2`, `zai/glm-5.3`, `zai/glm-5.3-flash`