StreamLake: Models and Prices

Model API platform that serves Kuaishou’s KAT models and open-weight models.

StreamLake served 1.75T tokens of other labs' open-weight models over Nov 2 to Nov 8, 2026 through a large public LLM router, #12 among providers.

Open-weight models

ModelFamilyShare of modelTokens, 7dInput $/MOutput $/MTokens/sUptime 3dContext
DeepSeek V4.1 Flash 1017DeepSeek1.0%588B$0.111$0.44462100.0%1.02M
DeepSeek V4.1 FlashDeepSeek2.7%476B$0.147$0.58886100.0%1.02M
DeepSeek V4 Flash 0423DeepSeek10.2%226B$0.083$0.16524100.0%1.02M
DeepSeek V4 Pro 0423DeepSeek26.0%130B$0.894$1.7940100.0%1.02M
DeepSeek V4 Flash 0731DeepSeek3.8%124B$0.132$0.39645100.0%1.02M
DeepSeek V4 Pro 0813DeepSeek12.8%81B$0.66$1.9858100.0%1.02M
GLM 5.2GLM7.2%56B$0.613$1.9346100.0%1.02M
GLM 5.3 FlashGLM0.3%44B$0.088$0.2954799.2%1.02M
MiniMax M3MiniMax2.8%16B$0.30$1.2090.599.9%1M
MiniMax M3.1 FlashMiniMax0.2%11B$0.135$0.545999.9%1M
MiMo-V2.6-ProMiMo--$0.522$1.043893.1%1M
Qwen3.8 27BQwen--$0.175$1.0560100.0%1.02M
Kimi K2.6Kimi--$0.599$2.524199.2%256K
Kimi K2.7 CodeKimi--$0.713$3.0062100.0%256K
GLM 5GLM--$0.60$1.924299.8%198K
GLM 5.1GLM--$0.966$3.0428100.0%200K
DeepSeek V3DeepSeek--$0.257$1.0346100.0%128K
Qwen3.5 397B A17BQwen--$0.60$3.6051100.0%256K
R1 0528DeepSeek--$0.571$2.2941100.0%128K
MiniMax M2.5MiniMax--$0.27$1.08102.5100.0%200K

List prices per million tokens as of November 8, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.

Company

Headquarters
China

Sources: Artificial Analysis.

Finance your GPUs

Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.

Prefer email? hello@amcompute.com