A
Alibaba
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-09-192026-10-18
Inference Latency
Qwen: Qwen3.6 Plus (free)1481ms TTFT · 44 TPS
Qwen: Qwen3.6 Plus Preview (free)903ms TTFT · 34 TPS
Qwen: Qwen3.7 Flash726ms TTFT · 56 TPS
Qwen: Qwen-Turbo534ms TTFT · 29 TPS
Qwen: Qwen3.7 Flash909ms TTFT · 60 TPS
Qwen: Qwen3.5-Flash586ms TTFT · 75 TPS
Qwen: Qwen3 VL 32B Instruct814ms TTFT · 56 TPS
Qwen: Qwen3 8B607ms TTFT · 46 TPS
Qwen: Qwen VL Plus221ms TTFT · 102 TPS
Qwen: Qwen3.8 Omni Flash1703ms TTFT · 44 TPS
Qwen: Qwen3.8 Flash881ms TTFT · 38 TPS
DeepSeek: DeepSeek V4 Flash 04231235ms TTFT · 72 TPS
Qwen: Qwen3.8 Flash798ms TTFT · 43 TPS
Qwen: Qwen3.5-35B-A3B679ms TTFT · 94 TPS
Qwen: Qwen3 VL 8B Thinking65049ms TTFT · 108 TPS
Qwen: Qwen3.6 Flash505ms TTFT · 90 TPS
Qwen: Qwen3.5-27B2337ms TTFT · 53 TPS
Qwen: Qwen3 Coder Flash834ms TTFT · 80 TPS
Qwen: Qwen3 30B A3B Thinking 2507314ms TTFT · 120 TPS
Qwen: Qwen3.5 Plus 2026-02-151217ms TTFT · 57 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Qwen: Qwen3.6 Plus (free) | $0.00 | $0.00 | 1481ms | 44 |
| Qwen: Qwen3.6 Plus Preview (free) | $0.00 | $0.00 | 903ms | 34 |
| Qwen: Qwen3.7 Flash | $0.03 | $0.13 | 726ms | 56 |
| Qwen: Qwen-Turbo | $0.03 | $0.13 | 534ms | 29 |
| Qwen: Qwen3.7 Flash | $0.03 | $0.15 | 909ms | 60 |
| Qwen: Qwen3.5-Flash | $0.07 | $0.26 | 586ms | 75 |
| Qwen: Qwen3 VL 32B Instruct | $0.10 | $0.42 | 814ms | 56 |
| Qwen: Qwen3 8B | $0.12 | $0.45 | 607ms | 46 |
| Qwen: Qwen VL Plus | $0.14 | $0.41 | 221ms | 102 |
| Qwen: Qwen3.8 Omni Flash | $0.15 | $0.47 | 1703ms | 44 |
| Qwen: Qwen3.8 Flash | $0.15 | $0.47 | 881ms | 38 |
| DeepSeek: DeepSeek V4 Flash 0423 | $0.15 | $0.30 | 1235ms | 72 |
| Qwen: Qwen3.8 Flash | $0.15 | $0.47 | 798ms | 43 |
| Qwen: Qwen3.5-35B-A3B | $0.16 | $1.30 | 679ms | 94 |
| Qwen: Qwen3 VL 8B Thinking | $0.18 | $2.10 | 65049ms | 108 |
| Qwen: Qwen3.6 Flash | $0.19 | $1.13 | 505ms | 90 |
| Qwen: Qwen3.5-27B | $0.20 | $1.56 | 2337ms | 53 |
| Qwen: Qwen3 Coder Flash | $0.20 | $0.98 | 834ms | 80 |
| Qwen: Qwen3 30B A3B Thinking 2507 | $0.20 | $2.40 | 314ms | 120 |
| Qwen: Qwen3.7 Plus (batch) | $0.23 | $0.92 | — | — |
| Qwen: Qwen3.5 Plus 2026-02-15 | $0.26 | $1.56 | 1217ms | 57 |
| Qwen: Qwen3.5-122B-A10B | $0.26 | $2.08 | 947ms | 42 |
| Qwen: Qwen-Plus | $0.26 | $0.78 | 505ms | 51 |
| Qwen: Qwen Plus 0728 (thinking) | $0.26 | $0.78 | 353ms | 63 |
| Qwen: Qwen Plus 0728 | $0.26 | $0.78 | 295ms | 50 |
| DeepSeek: DeepSeek V4.1 Flash | $0.30 | $1.20 | 1139ms | 109 |
| Qwen: Qwen3.5 Plus 2026-04-20 | $0.30 | $1.80 | 1100ms | 50 |
| Qwen: Qwen3.7 Plus | $0.32 | $1.28 | 1136ms | 36 |
| Qwen: Qwen3.7 Plus | $0.32 | $1.28 | 1376ms | 34 |
| Qwen: Qwen3.6 Plus | $0.33 | $1.95 | 901ms | 42 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.35 | $1.06 | 1729ms | 85 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.37 | $1.12 | 1925ms | 95 |
| Qwen: Qwen3.5 397B A17B | $0.39 | $2.34 | 1160ms | 42 |
| Qwen: Qwen3 VL 235B A22B Thinking | $0.40 | $4.00 | 647ms | 47 |
| Qwen: Qwen3.8 27B | $0.43 | $2.55 | 2722ms | 45 |
| Qwen: Qwen3.6 27B | $0.45 | $2.70 | 1065ms | 56 |
| Qwen: Qwen3 235B A22B | $0.45 | $1.82 | 622ms | 45 |
| Qwen: Qwen VL Max | $0.52 | $2.08 | 1111ms | 37 |
| Qwen: Qwen3 Coder Plus | $0.65 | $3.25 | 1225ms | 40 |
| Qwen: Qwen3 Max Thinking | $0.78 | $3.90 | 681ms | 37 |
| Qwen: Qwen3 Max | $0.78 | $3.90 | 878ms | 36 |
| MoonshotAI: Kimi K2.7 Code | $0.95 | $4.00 | 1398ms | 59 |
| Z.ai: GLM 5.2 | $0.97 | $3.04 | 1243ms | 89 |
| Qwen: Qwen3.6 Max Preview | $1.03 | $6.16 | 1886ms | 58 |
| Qwen: Qwen-Max | $1.04 | $4.16 | 520ms | 51 |
| Z.ai: GLM 5.2 | $1.12 | $3.52 | 1468ms | 61 |
| DeepSeek: DeepSeek V4 Pro 0813 | $1.12 | $3.37 | 1299ms | 57 |
| Z.ai: GLM 5.3 | $1.19 | $3.74 | 2211ms | 74 |
| DeepSeek: DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 1104ms | 49 |
| Z.ai: GLM 5.1 | $1.33 | $4.18 | 1665ms | 52 |
| DeepSeek: DeepSeek V4 Pro 0423 | $1.42 | $2.83 | 1878ms | 44 |
| Qwen: Qwen3.7 Max | $1.48 | $4.43 | 1074ms | 74 |
| DeepSeek: DeepSeek V4 Pro 0423 | $1.56 | $3.12 | 1756ms | 47 |
| Qwen: Qwen3.8 2.4T A95B | $2.00 | $6.00 | 10267ms | 40 |
| Qwen: Qwen3.8 Max | $2.00 | $6.00 | 888ms | 42 |
| Qwen: Qwen3.7 Max | $2.00 | $6.00 | 1149ms | 67 |
| Qwen: Qwen3.8 Max (0902) | $2.00 | $6.00 | 1549ms | 39 |
| Qwen: Qwen3.8 Max (0902) | $2.00 | $6.00 | 3086ms | 33 |
| Z.ai: GLM 5.2 | $2.31 | $7.26 | 761ms | 94 |
| Z.ai: GLM 5.3 Prime | $2.80 | $8.80 | 1840ms | 61 |
| Z.ai: GLM 5.3 | $2.80 | $8.80 | 2236ms | 56 |
| MoonshotAI: Kimi K3 | $3.45 | $17.25 | 2795ms | 35 |
| Qwen: Qwen3.8 Max Prime | $4.00 | $12.00 | 1442ms | 74 |
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.