| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 DeepSeek V3 0324 | siliconflow/fp8 | 164K | $0.25 | $1.00 | — | — | 100.00% |
| DeepSeek V3.1 | siliconflow/fp8 | 164K | $0.27 | $1.00 | — | — | 100.00% |
| DeepSeek V3.1 Terminus | siliconflow/fp8 | 164K | $0.27 | $1.00 | — | — | 100.00% |
| DeepSeek V3.2 | siliconflow/fp8 | 164K | $0.259 | $0.80 | $0.14 | — | 99.58% |
| DeepSeek V3.2 Exp | siliconflow/fp8 | 164K | $0.27 | $0.41 | — | — | 100.00% |
| DeepSeek V4 Flash 0423 | siliconflow/fp8 | 1M | $0.13 | $0.28 | $0.028 | — | 94.03% |
| DeepSeek V4 Flash 0731 | siliconflow/fp8 | 1M | $0.22 | $0.66 | $0.028 | — | 72.41% |
| DeepSeek V4 Pro 0423 | siliconflow/fp8 | 1M | $1.00 | $1.50 | $0.135 | — | 99.86% |
| DeepSeek V4 Pro 0813 | siliconflow/fp8 | 1M | $1.32 | $3.96 | $0.044 | — | 99.85% |
| DeepSeek V4.1 Flash | siliconflow/fp8 | 1M | $0.30 | $1.20 | $0.006 | — | 99.93% |
| DeepSeek V4.1 Flash 1017 | siliconflow/fp8 | 1M | $0.30 | $0.55 | $0.006 | — | 99.93% |
 GLM 4.5 Air | siliconflow/fp8 | 131K | $0.14 | $0.86 | — | — | 100.00% |
| GLM 5 | siliconflow/fp8 | 205K | $0.95 | $2.55 | $0.20 | — | 99.04% |
| GLM 5.1 | siliconflow/fp8 | 205K | $1.19 | $3.74 | $0.60 | — | 99.56% |
| GLM 5.2 | siliconflow/fp8 | 1M | $0.70 | $2.20 | $0.13 | — | 99.93% |
| GLM 5.3 | siliconflow/fp8 | 1M | $0.70 | $2.20 | $0.13 | — | 100.00% |
| GLM 5.3 Flash | siliconflow/fp8 | 1M | $0.15 | $0.50 | $0.03 | — | 99.15% |
 Gemma 4 26B A4B | siliconflow/fp8 | 262K | $0.14 | $0.40 | $0.05 | — | 100.00% |
| Gemma 4 31B | siliconflow/fp8 | 262K | $0.75 | $1.00 | $0.25 | — | 98.57% |
 Hunyuan A13B Instruct | siliconflow/fp8 | 131K | $0.14 | $0.57 | — | — | 100.00% |
| Hy4 preview | siliconflow/fp8 | 1M | $0.834 | $2.501 | $0.042 | — | 100.00% |
| Kev 4B | siliconflow/fp8 | 8K | $0.042 | $0.00 | — | — | 100.00% |
 Kimi K2.5 | siliconflow/int4 | 262K | $0.50 | $2.50 | $0.15 | — | 100.00% |
| Kimi K2.6 | siliconflow/fp8 | 262K | $0.77 | $3.40 | $0.14 | — | 100.00% |
| Kimi K2.7 Code | siliconflow/fp8 | 262K | $0.8592 | $3.80 | $0.1799 | — | 100.00% |
 Qwen3 30B A3B Instruct 2507 | siliconflow/fp8 | 262K | $0.09 | $0.30 | — | — | 98.24% |
| Qwen3 32B | siliconflow/fp8 | 131K | $0.14 | $0.57 | — | — | 96.90% |
| Qwen3 Coder 30B A3B Instruct | siliconflow/fp8 | 262K | $0.07 | $0.28 | — | — | 96.42% |
| Qwen3 Embedding 8B | siliconflow/fp8 | 33K | $0.04 | $0.00 | — | — | 91.74% |
| Qwen3 VL 30B A3B Instruct | siliconflow/fp8 | 262K | $0.29 | $1.00 | — | — | 48.60% |
| Qwen3 VL 30B A3B Thinking | siliconflow/fp8 | 262K | $0.29 | $1.00 | — | — | 100.00% |
| Qwen3.5-122B-A10B | siliconflow/fp8 | 262K | $0.26 | $2.08 | — | — | 94.46% |
| Qwen3.5-27B | siliconflow/fp8 | 262K | $0.25 | $2.00 | — | — | 95.92% |
| Qwen3.5-35B-A3B | siliconflow/fp8 | 262K | $0.24 | $1.80 | $0.15 | — | 100.00% |
| Qwen3.5-9B | siliconflow/fp8 | 262K | $0.10 | $0.15 | — | — | 92.85% |
| Qwen3.6 27B | siliconflow/fp8 | 262K | $0.30 | $3.20 | — | — | 95.76% |
| Qwen3.6 35B A3B | siliconflow/fp8 | 262K | $0.24 | $1.80 | $0.15 | — | 99.17% |
| Qwen3.8 2.4T A95B | siliconflow/fp8 | 1M | $2.00 | $6.00 | $0.25 | — | 100.00% |
| R1 0528 | siliconflow/fp8 | 164K | $0.50 | $2.18 | — | — | 98.91% |
 Step 3.5 Flash | siliconflow/fp8 | 262K | $0.10 | $0.30 | — | — | 99.86% |
 gpt-oss-120b | siliconflow/fp8 | 131K | $0.15 | $0.60 | $0.075 | — | 100.00% |
| gpt-oss-20b | siliconflow/fp8 | 131K | $0.04 | $0.18 | — | — | 94.74% |