SiliconFlow pricing overview
TokenWatch tracks 41 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Cheapest input price: gpt-oss-20b at $0.040 per million input tokens and $0.180 per million output tokens. 23 of 41 text models publish a cache-read price; 41 carry a zero-data-retention tag.
SiliconFlow text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| deepseek | siliconflow | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.300 | $1.20 | $0.0060 | $0.019 |
| deepseek | siliconflow | DeepSeek: DeepSeek V4.1 Flash | $0.300 | $1.20 | $0.0060 | $0.019 |
| deepseek | siliconflow | DeepSeek: DeepSeek V4 Flash 0423 | $0.130 | $0.280 | $0.028 | $0.032 |
| z-ai | siliconflow | Z.ai: GLM 5.3 Flash | $0.150 | $0.500 | $0.030 | $0.035 |
| deepseek | siliconflow | DeepSeek: DeepSeek V4 Flash 0731 | $0.220 | $0.660 | $0.028 | $0.036 |
| openai | siliconflow | OpenAI: gpt-oss-20b | $0.040 | $0.180 | — | $0.041 |
| deepseek | siliconflow | DeepSeek: DeepSeek V4 Flash Vision Exp | $0.440 | $1.32 | $0.028 | $0.045 |
| siliconflow | Google: Gemma 4 26B A4B | $0.140 | $0.400 | $0.050 | $0.054 | |
| qwen | siliconflow | Qwen: Qwen3 Coder 30B A3B Instruct | $0.070 | $0.280 | — | $0.071 |
| tencent | siliconflow | Tencent: Hy4 preview | $0.834 | $2.50 | $0.042 | $0.074 |
| openai | siliconflow | OpenAI: gpt-oss-120b | $0.150 | $0.600 | $0.075 | $0.080 |
| qwen | siliconflow | Qwen: Qwen3 30B A3B Instruct 2507 | $0.090 | $0.300 | — | $0.091 |
| deepseek | siliconflow | DeepSeek: DeepSeek V4 Pro 0813 | $1.32 | $3.96 | $0.044 | $0.095 |
| qwen | siliconflow | Qwen: Qwen3.5-9B | $0.100 | $0.150 | — | $0.100 |
| stepfun | siliconflow | StepFun: Step 3.5 Flash | $0.100 | $0.300 | — | $0.101 |
| tencent | siliconflow | Tencent: Hunyuan A13B Instruct | $0.140 | $0.570 | — | $0.142 |
| qwen | siliconflow | Qwen: Qwen3 32B | $0.140 | $0.570 | — | $0.142 |
| z-ai | siliconflow | Z.ai: GLM 4.5 Air | $0.140 | $0.860 | — | $0.144 |
| deepseek | siliconflow | DeepSeek: DeepSeek V3.2 | $0.259 | $0.800 | $0.140 | $0.146 |
| z-ai | siliconflow | Z.ai: GLM 5.3 | $0.700 | $2.20 | $0.130 | $0.155 |
| z-ai | siliconflow | Z.ai: GLM 5.2 | $0.700 | $2.20 | $0.130 | $0.155 |
| qwen | siliconflow | Qwen: Qwen3.6 35B A3B | $0.240 | $1.80 | $0.150 | $0.160 |
| qwen | siliconflow | Qwen: Qwen3.5-35B-A3B | $0.240 | $1.80 | $0.150 | $0.160 |
| moonshot | siliconflow | MoonshotAI: Kimi K2.5 | $0.500 | $2.50 | $0.150 | $0.170 |
| deepseek | siliconflow | DeepSeek: DeepSeek V4 Pro 0423 | $1.00 | $3.14 | $0.135 | $0.172 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.