S
SiliconFlow
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-09-192026-10-18
Inference Latency
Nex AGI: Nex-N2-Pro (free)1673ms TTFT · 74 TPS
Tencent: Hy3 preview (free)3863ms TTFT · 47 TPS
OpenAI: gpt-oss-20b1065ms TTFT · 48 TPS
Qwen: Qwen3 Coder 30B A3B Instruct1017ms TTFT · 23 TPS
Qwen: Qwen3 30B A3B Instruct 25071002ms TTFT · 19 TPS
Qwen: Qwen3.5-9B1353ms TTFT · 51 TPS
StepFun: Step 3.5 Flash1148ms TTFT · 60 TPS
DeepSeek: DeepSeek V4 Flash 0423902ms TTFT · 38 TPS
Nex AGI: DeepSeek V3.1 Nex N12319ms TTFT · 32 TPS
Tencent: Hunyuan A13B Instruct2289ms TTFT · 35 TPS
Z.ai: GLM 4.5 Air1412ms TTFT · 33 TPS
Google: Gemma 4 26B A4B 1947ms TTFT · 17 TPS
Qwen: Qwen3 32B1818ms TTFT · 30 TPS
Z.ai: GLM 5.3 Flash2495ms TTFT · 41 TPS
OpenAI: gpt-oss-120b1158ms TTFT · 47 TPS
Qwen: QwQ 32B1325ms TTFT · 44 TPS
DeepSeek: DeepSeek V4 Flash 07311317ms TTFT · 45 TPS
Qwen: Qwen3.6 35B A3B988ms TTFT · 56 TPS
Qwen: Qwen3.5-35B-A3B1658ms TTFT · 60 TPS
Qwen: Qwen3.5-27B2322ms TTFT · 18 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Nex AGI: Nex-N2-Pro (free) | $0.00 | $0.00 | 1673ms | 74 |
| Tencent: Hy3 preview (free) | $0.00 | $0.00 | 3863ms | 47 |
| OpenAI: gpt-oss-20b | $0.04 | $0.18 | 1065ms | 48 |
| Qwen: Qwen3 Coder 30B A3B Instruct | $0.07 | $0.28 | 1017ms | 23 |
| Qwen: Qwen3 30B A3B Instruct 2507 | $0.09 | $0.30 | 1002ms | 19 |
| Qwen: Qwen3.5-9B | $0.10 | $0.15 | 1353ms | 51 |
| StepFun: Step 3.5 Flash | $0.10 | $0.30 | 1148ms | 60 |
| DeepSeek: DeepSeek V4 Flash 0423 | $0.13 | $0.28 | 902ms | 38 |
| Nex AGI: DeepSeek V3.1 Nex N1 | $0.14 | $0.50 | 2319ms | 32 |
| Tencent: Hunyuan A13B Instruct | $0.14 | $0.57 | 2289ms | 35 |
| Z.ai: GLM 4.5 Air | $0.14 | $0.86 | 1412ms | 33 |
| Google: Gemma 4 26B A4B | $0.14 | $0.40 | 1947ms | 17 |
| Qwen: Qwen3 32B | $0.14 | $0.57 | 1818ms | 30 |
| Z.ai: GLM 5.3 Flash | $0.15 | $0.50 | 2495ms | 41 |
| OpenAI: gpt-oss-120b | $0.15 | $0.60 | 1158ms | 47 |
| Qwen: QwQ 32B | $0.15 | $0.58 | 1325ms | 44 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.22 | $0.66 | 1317ms | 45 |
| Qwen: Qwen3.6 35B A3B | $0.24 | $1.80 | 988ms | 56 |
| Qwen: Qwen3.5-35B-A3B | $0.24 | $1.80 | 1658ms | 60 |
| Qwen: Qwen3.5-27B | $0.25 | $2.00 | 2322ms | 18 |
| DeepSeek: DeepSeek V3 0324 | $0.25 | $1.00 | 1936ms | 22 |
| DeepSeek: DeepSeek V3.2 | $0.26 | $0.80 | 2201ms | 16 |
| Qwen: Qwen3.5-122B-A10B | $0.26 | $2.08 | 1219ms | 44 |
| DeepSeek: DeepSeek V3.1 | $0.27 | $1.00 | 2093ms | 15 |
| DeepSeek: DeepSeek V3.2 Exp | $0.27 | $0.41 | 2226ms | 16 |
| DeepSeek: DeepSeek V3.1 Terminus | $0.27 | $1.00 | 2394ms | 17 |
| Qwen: Qwen3 VL 30B A3B Thinking | $0.29 | $1.00 | 913ms | 81 |
| Qwen: Qwen3 VL 30B A3B Instruct | $0.29 | $1.00 | 2584ms | 17 |
| DeepSeek: DeepSeek V4.1 Flash | $0.30 | $1.20 | 1455ms | 75 |
| Qwen: Qwen3.6 27B | $0.30 | $3.20 | 8444ms | 17 |
| DeepSeek: DeepSeek V4 Flash Vision Exp | $0.44 | $1.32 | 1814ms | 112 |
| MoonshotAI: Kimi K2.5 | $0.50 | $2.50 | 1681ms | 23 |
| DeepSeek: R1 0528 | $0.50 | $2.18 | 1438ms | 18 |
| Z.ai: GLM 5.2 | $0.70 | $2.20 | 1262ms | 81 |
| Z.ai: GLM 5.3 | $0.70 | $2.20 | 3029ms | 54 |
| Google: Gemma 4 31B | $0.75 | $1.00 | 2960ms | 12 |
| MoonshotAI: Kimi K2.6 | $0.77 | $3.40 | 1252ms | 24 |
| Tencent: Hy4 preview | $0.83 | $2.50 | 1619ms | 36 |
| MoonshotAI: Kimi K2.7 Code | $0.86 | $3.80 | 3379ms | 17 |
| Z.ai: GLM 5 | $0.95 | $2.55 | 2139ms | 52 |
| Z.ai: GLM 5.1 | $1.19 | $3.74 | 1975ms | 40 |
| DeepSeek: DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 1726ms | 49 |
| DeepSeek: DeepSeek V4 Pro 0423 | $1.50 | $3.14 | 1680ms | 36 |
| Qwen: Qwen3.8 2.4T A95B | $2.00 | $6.00 | 3481ms | 30 |
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.