---
id: "tensorx"
gateways: ["requesty"]
models: 16
endpoints: 16
tokens_week: 0
token_share: "0.0%"
rank: 118
cheapest_on: "1 of 15 shared models"
cheaper_than: "14% of offers at the median"
latency_p50_ms: 1275
tokens_per_second: 151
trains_on_some: false
retains_on_some: false
quantization: "fp8 (4), fp4 (1), int4 (1), mxfp4 (1)"
---
# tensorx

`alibaba/qwen3.8-2.4t-a95b`, `alibaba/qwen3.8-flash-next`, `deepseek/deepseek-v4.1-flash`, `deepseek/deepseek-v4.1-flash-1017`, `deepseek/deepseek-v4-flash-0731`, `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-pro-0424`, `deepseek/deepseek-v4-pro-0813`, `minimax/minimax-m3`, `minimax/minimax-m3.1-flash`, `moonshot/kimi-k2.7-code`, `moonshot/kimi-k3`, `moonshot/kimi-k3.1-pro`, `zai/glm-5.2`, `zai/glm-5.3`, `zai/glm-5.3-flash`