SiliconFlow API pricing
15 SiliconFlow models. Source: https://www.siliconflow.com/pricing
- Provider type
- Inference host
- Headquarters
- China (outside EU)
- Regions
- unknown
- EU data residency
- unknown
- Residency notes
- International platform siliconflow.com is operated by SILICONFLOW LABS PTE. LTD. (Singapore; Singapore law/PDPA, not available in mainland China, which uses siliconflow.cn); parent company Beijing SiliconFlow Technology (Haidian, Beijing). Inference regions not stated on the pricing page.
- Residency source
- https://docs.siliconflow.com/en/legals/terms-of-service
HQ country is from public company information; regions and EU residency are only filled from the cited source page, otherwise 'unknown'.
Blend input:output
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| SiliconFlow Inference host | gpt-oss-20b | $0.04 | $0.18 | — | $0.075 | 131K | unknown |
| SiliconFlow Inference host | gpt-oss-120b | $0.05 | $0.45 | — | $0.15 | 131K | unknown |
| SiliconFlow Inference host | gemma-4-26B-A4B-it | $0.14 | $0.40 | $0.05 | $0.205 | 262K | unknown |
| SiliconFlow Inference host | GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | $0.237 | 1.049M | unknown |
| SiliconFlow Inference host | DeepSeek-V4.1-Flash | $0.15 | $0.60 | $0.003 | $0.262 | 1.049M | unknown |
| SiliconFlow Inference host | DeepSeek-V4-Flash-0731 | $0.22 | $0.66 | $0.014 | $0.33 | 1.049M | unknown |
| SiliconFlow Inference host | MiniMax-M3 | $0.30 | $1.20 | $0.06 | $0.525 | 1.049M | unknown |
| SiliconFlow Inference host | Qwen3.5-122B-A10B | $0.26 | $2.08 | — | $0.715 | 262K | unknown |
| SiliconFlow Inference host | gemma-4-31B-it | $0.75 | $1.00 | $0.25 | $0.813 | 262K | unknown |
| SiliconFlow Inference host | Kimi-K2.7-Code | $0.859 | $3.80 | $0.18 | $1.59 | 262K | unknown |
| SiliconFlow Inference host | DeepSeek-V4-Pro-0813 | $1.32 | $3.96 | $0.044 | $1.98 | 1.049M | unknown |
| SiliconFlow Inference host | GLM-5.2 | $1.30 | $4.09 | $0.26 | $2.00 | 1.049M | unknown |
| SiliconFlow Inference host | GLM-5.3 | $1.40 | $4.40 | $0.26 | $2.15 | 1.049M | unknown |
| SiliconFlow Inference host | Qwen3.8-2.4T-A95B | $2.00 | $6.00 | $0.25 | $3.00 | 1.049M | unknown |
| SiliconFlow Inference host | Kimi-K3 | $2.70 | $13.50 | $0.27 | $5.40 | 1.049M | unknown |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with € or CHF: those are as published and not converted. Click a header to sort. 15 models.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.