LIVE
Models: —+Providers: —+Cheapest H100: $2.49/hrUpdated: 04:29 PMModels: —+Providers: —+Cheapest H100: $2.49/hrUpdated: 04:29 PM
Marketplace
Providers Models
S

StreamLake

AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating

30-Day Uptime

96.7%
2026-05-222026-06-20

Inference Latency

Qwen: Qwen3 30B A3B Instruct 25072264ms TTFT · 30 TPS
DeepSeek: DeepSeek V4 Flash1535ms TTFT · 13 TPS
Qwen: Qwen3 Coder Next1769ms TTFT · 30 TPS
DeepSeek: DeepSeek V3825ms TTFT · 25 TPS
Qwen: Qwen3 235B A22B Instruct 2507711ms TTFT · 34 TPS
DeepSeek: DeepSeek V3.21379ms TTFT · 17 TPS
MiniMax: MiniMax M2.52667ms TTFT · 40 TPS
Kwaipilot: KAT-Coder-Pro V22879ms TTFT · 33 TPS
DeepSeek: DeepSeek V3.1 Terminus1280ms TTFT · 25 TPS
Z.ai: GLM 4.71295ms TTFT · 55 TPS
MoonshotAI: Kimi K2.51922ms TTFT · 31 TPS
DeepSeek: R1 05282769ms TTFT · 26 TPS
Qwen: Qwen3.5 397B A17B1036ms TTFT · 53 TPS
Z.ai: GLM 51740ms TTFT · 66 TPS
MoonshotAI: Kimi K2.61088ms TTFT · 60 TPS
DeepSeek: DeepSeek V4 Pro1836ms TTFT · 45 TPS
Z.ai: GLM 5.11785ms TTFT · 40 TPS
Z.ai: GLM 5.21875ms TTFT · 30 TPS

Inference Models

ModelInput $/MOutput $/MTTFTTPS
Qwen: Qwen3 30B A3B Instruct 2507$0.05$0.192264ms30
DeepSeek: DeepSeek V4 Flash$0.13$0.271535ms13
Qwen: Qwen3 Coder Next$0.18$0.901769ms30
DeepSeek: DeepSeek V3$0.20$0.80825ms25
Kwaipilot: KAT-Coder-Pro V1$0.21$0.83
Qwen: Qwen3 235B A22B Instruct 2507$0.21$0.84711ms34
DeepSeek: DeepSeek V3.2$0.23$0.341379ms17
MiniMax: MiniMax M2.5$0.27$1.082667ms40
Kwaipilot: KAT-Coder-Pro V2$0.30$1.202879ms33
DeepSeek: DeepSeek V3.1 Terminus$0.34$1.031280ms25
Z.ai: GLM 4.7$0.48$1.761295ms55
MoonshotAI: Kimi K2.5$0.54$2.701922ms31
DeepSeek: R1 0528$0.57$2.292769ms26
Qwen: Qwen3.5 397B A17B$0.60$3.601036ms53
Z.ai: GLM 5$0.65$2.081740ms66
MoonshotAI: Kimi K2.6$0.86$3.601088ms60
DeepSeek: DeepSeek V4 Pro$0.87$1.741836ms45
Z.ai: GLM 5.1$0.98$3.081785ms40
Z.ai: GLM 5.2$1.40$4.401875ms30

Community Reviews

4.5★★★★★(2 reviews)
clouduser42
★★★★★2025-06-15

Reliable service, great API documentation.

mlresearcher
★★★★2025-06-10

Good performance but support could be faster.