Host
SiliconFlow
0 models created · 20 host offerings
Active Models
0
Host Offerings
20
Cheapest Input
—
Largest Context
—
Models Hosted
Page 1 of 1 · 20 offerings
| Model | Creator | In / M | Out / M | Context | Quant | Uptime 30m | Latency | TPS |
|---|---|---|---|---|---|---|---|---|
| Z.ai: GLM 5 SiliconFlow | z-ai/glm-5-20260211 | Z Ai | $0.950 | $2.55 | 205K | fp8 | 100.00% | 2572ms | 41.0 |
| Z.ai: GLM 4.5 Air SiliconFlow | z-ai/glm-4.5-air | Z Ai | $0.140 | $0.860 | 131K | fp8 | 100.00% | 1609ms | 22.5 |
| Qwen: Qwen3.5-122B-A10B SiliconFlow | qwen/qwen3.5-122b-a10b-20260224 | Alibaba | $0.260 | $2.08 | 262K | fp8 | 100.00% | 3699ms | 75.0 |
| Z.ai: GLM 5.1 SiliconFlow | z-ai/glm-5.1-20260406 | Z Ai | $1.19 | $3.74 | 205K | fp8 | 100.00% | 1599ms | 49.0 |
| MiniMax: MiniMax M2.5 SiliconFlow | minimax/minimax-m2.5-20260211 | Minimax | $0.300 | $1.20 | 197K | fp8 | 100.00% | 1295ms | 44.5 |
| DeepSeek: DeepSeek V4 Pro 0813 SiliconFlow | deepseek/deepseek-v4-pro-20260813 | Deepseek | $1.32 | $3.96 | 1.0M | fp8 | 99.83% | 1613ms | 51.0 |
| Qwen: Qwen3 Coder 30B A3B Instruct SiliconFlow | qwen/qwen3-coder-30b-a3b-instruct | Alibaba | $0.070 | $0.280 | 262K | fp8 | 99.76% | 1402ms | 28.0 |
| Qwen: Qwen3.5-27B SiliconFlow | qwen/qwen3.5-27b-20260224 | Alibaba | $0.250 | $2.00 | 262K | fp8 | 99.71% | 1246ms | 10.0 |
| Z.ai: GLM 5.2 SiliconFlow | z-ai/glm-5.2-20260616 | Z Ai | $1.19 | $3.74 | 1.0M | fp8 | 99.50% | 4834ms | 34.0 |
| Qwen: Qwen3 VL 30B A3B Instruct SiliconFlow | qwen/qwen3-vl-30b-a3b-instruct | Alibaba | $0.290 | $1.00 | 262K | fp8 | 99.39% | 1600ms | 14.0 |
| DeepSeek: DeepSeek V4 Flash 0731 SiliconFlow | deepseek/deepseek-v4-flash-20260731 | Deepseek | $0.140 | $0.280 | 1.0M | fp8 | 98.58% | 1656ms | 53.0 |
| Google: Gemma 4 26B A4B SiliconFlow | google/gemma-4-26b-a4b-it-20260403 | $0.120 | $0.400 | 262K | fp8 | 98.27% | 1214ms | 25.0 | |
| Qwen: Qwen3 30B A3B Instruct 2507 SiliconFlow | qwen/qwen3-30b-a3b-instruct-2507 | Alibaba | $0.090 | $0.300 | 262K | fp8 | 98.27% | 1977ms | 11.0 |
| DeepSeek: DeepSeek V4 Pro 0423 SiliconFlow | deepseek/deepseek-v4-pro-20260423 | Deepseek | $1.50 | $3.14 | 1.0M | fp8 | 97.41% | 1446ms | 50.0 |
| DeepSeek: DeepSeek V4 Flash 0423 SiliconFlow | deepseek/deepseek-v4-flash-20260423 | Deepseek | $0.130 | $0.280 | 1.0M | fp8 | 97.07% | 1639ms | 52.0 |
| Qwen: Qwen3 32B SiliconFlow | qwen/qwen3-32b-04-28 | — | $0.140 | $0.570 | 131K | fp8 | 96.72% | 1673ms | 13.0 |
| Qwen: Qwen3.6 27B SiliconFlow | qwen/qwen3.6-27b-20260422 | Alibaba | $0.300 | $3.20 | 262K | fp8 | 93.31% | 1525ms | 27.0 |
| Nex AGI: Nex-N2-Pro SiliconFlow | nex-agi/nex-n2-pro | Nex Agi | $0.500 | $2.50 | 262K | — | — | 893ms | 114.0 |
| Qwen: Qwen3 VL 30B A3B Thinking SiliconFlow | qwen/qwen3-vl-30b-a3b-thinking | Alibaba | $0.290 | $1.00 | 262K | fp8 | — | 1110ms | 88.0 |
| Qwen: Qwen3.5-35B-A3B SiliconFlow | qwen/qwen3.5-35b-a3b-20260224 | Alibaba | $0.240 | $1.80 | 262K | fp8 | — | 1372ms | 60.0 |
- Z.ai: GLM 5Z Ai · fp8$0.950 in$2.55 out205K ctx100.00% up
- Z.ai: GLM 4.5 AirZ Ai · fp8$0.140 in$0.860 out131K ctx100.00% up
- Qwen: Qwen3.5-122B-A10BAlibaba · fp8$0.260 in$2.08 out262K ctx100.00% up
- Z.ai: GLM 5.1Z Ai · fp8$1.19 in$3.74 out205K ctx100.00% up
- MiniMax: MiniMax M2.5Minimax · fp8$0.300 in$1.20 out197K ctx100.00% up
- DeepSeek: DeepSeek V4 Pro 0813Deepseek · fp8$1.32 in$3.96 out1.0M ctx99.83% up
- Qwen: Qwen3 Coder 30B A3B InstructAlibaba · fp8$0.070 in$0.280 out262K ctx99.76% up
- Qwen: Qwen3.5-27BAlibaba · fp8$0.250 in$2.00 out262K ctx99.71% up
- Z.ai: GLM 5.2Z Ai · fp8$1.19 in$3.74 out1.0M ctx99.50% up
- Qwen: Qwen3 VL 30B A3B InstructAlibaba · fp8$0.290 in$1.00 out262K ctx99.39% up
- DeepSeek: DeepSeek V4 Flash 0731Deepseek · fp8$0.140 in$0.280 out1.0M ctx98.58% up
- Google: Gemma 4 26B A4BGoogle · fp8$0.120 in$0.400 out262K ctx98.27% up
- Qwen: Qwen3 30B A3B Instruct 2507Alibaba · fp8$0.090 in$0.300 out262K ctx98.27% up
- DeepSeek: DeepSeek V4 Pro 0423Deepseek · fp8$1.50 in$3.14 out1.0M ctx97.41% up
- DeepSeek: DeepSeek V4 Flash 0423Deepseek · fp8$0.130 in$0.280 out1.0M ctx97.07% up
- Qwen: Qwen3 32B· fp8$0.140 in$0.570 out131K ctx96.72% up
- Qwen: Qwen3.6 27BAlibaba · fp8$0.300 in$3.20 out262K ctx93.31% up
- Nex AGI: Nex-N2-ProNex Agi$0.500 in$2.50 out262K ctx
- Qwen: Qwen3 VL 30B A3B ThinkingAlibaba · fp8$0.290 in$1.00 out262K ctx
- Qwen: Qwen3.5-35B-A3BAlibaba · fp8$0.240 in$1.80 out262K ctx
