S
StreamLake
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-07-212026-08-19
Inference Latency
Qwen: Qwen3 30B A3B Instruct 25071729ms TTFT · 20 TPS
DeepSeek: DeepSeek V4 Flash 07314334ms TTFT · 29 TPS
DeepSeek: DeepSeek V4 Flash 04232280ms TTFT · 22 TPS
Kwaipilot: KAT-Coder-Air V2.52303ms TTFT · 98 TPS
Qwen: Qwen3 Coder Next833ms TTFT · 33 TPS
Qwen: Qwen3 235B A22B Instruct 2507811ms TTFT · 31 TPS
DeepSeek: DeepSeek V3.21353ms TTFT · 23 TPS
DeepSeek: DeepSeek V31458ms TTFT · 28 TPS
MiniMax: MiniMax M2.5616ms TTFT · 68 TPS
MiniMax: MiniMax M31762ms TTFT · 78 TPS
Kwaipilot: KAT-Coder-Pro V2617ms TTFT · 14 TPS
DeepSeek: DeepSeek V3.1 Terminus1283ms TTFT · 3 TPS
Z.ai: GLM 4.72221ms TTFT · 29 TPS
Xiaomi: MiMo-V2.5-Pro2299ms TTFT · 30 TPS
MoonshotAI: Kimi K2.51556ms TTFT · 33 TPS
DeepSeek: R1 05283502ms TTFT · 40 TPS
MoonshotAI: Kimi K2.61852ms TTFT · 34 TPS
Z.ai: GLM 52720ms TTFT · 39 TPS
Qwen: Qwen3.5 397B A17B2342ms TTFT · 46 TPS
DeepSeek: DeepSeek V4 Pro 04232173ms TTFT · 38 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Qwen: Qwen3 30B A3B Instruct 2507 | $0.05 | $0.19 | 1729ms | 20 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.08 | $0.16 | 4334ms | 29 |
| DeepSeek: DeepSeek V4 Flash 0423 | $0.08 | $0.17 | 2280ms | 22 |
| Kwaipilot: KAT-Coder-Air V2.5 | $0.15 | $0.60 | 2303ms | 98 |
| Qwen: Qwen3 Coder Next | $0.18 | $0.90 | 833ms | 33 |
| Kwaipilot: KAT-Coder-Pro V1 | $0.21 | $0.83 | — | — |
| Qwen: Qwen3 235B A22B Instruct 2507 | $0.21 | $0.84 | 811ms | 31 |
| DeepSeek: DeepSeek V3.2 | $0.21 | $0.32 | 1353ms | 23 |
| DeepSeek: DeepSeek V3 | $0.26 | $1.03 | 1458ms | 28 |
| MiniMax: MiniMax M2.5 | $0.27 | $1.08 | 616ms | 68 |
| MiniMax: MiniMax M3 | $0.30 | $1.20 | 1762ms | 78 |
| Kwaipilot: KAT-Coder-Pro V2 | $0.30 | $1.20 | 617ms | 14 |
| DeepSeek: DeepSeek V3.1 Terminus | $0.34 | $1.03 | 1283ms | 3 |
| Z.ai: GLM 4.7 | $0.48 | $1.76 | 2221ms | 29 |
| Xiaomi: MiMo-V2.5-Pro | $0.52 | $1.04 | 2299ms | 30 |
| MoonshotAI: Kimi K2.5 | $0.54 | $2.70 | 1556ms | 33 |
| DeepSeek: R1 0528 | $0.57 | $2.29 | 3502ms | 40 |
| MoonshotAI: Kimi K2.6 | $0.60 | $2.52 | 1852ms | 34 |
| Z.ai: GLM 5 | $0.60 | $1.92 | 2720ms | 39 |
| Qwen: Qwen3.5 397B A17B | $0.60 | $3.60 | 2342ms | 46 |
| DeepSeek: DeepSeek V4 Pro 0423 | $0.69 | $1.39 | 2173ms | 38 |
| Z.ai: GLM 5.2 | $0.73 | $2.31 | 1781ms | 41 |
| Kwaipilot: KAT-Coder-Pro V2.5 | $0.74 | $2.96 | 1503ms | 61 |
| Z.ai: GLM 5.1 | $0.97 | $3.04 | 4887ms | 18 |
| DeepSeek: DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 2225ms | 54 |
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.