SiliconFlow
GlobalInference hostSiliconFlow runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.
Other region:SiliconFlowCN
Models48
- Cheapest for
- 2 models
- Serves
- 1 model types
Visits in September 2026309K−27.8%Unique visitors 146K
- Apr
- May
- Jun
- Jul
- Aug
- Sep
Models by type
Models on SiliconFlow
| Model | Input | Output | vs official | Context |
|---|---|---|---|---|
| Kimi K3Moonshot AI | $2.70/1M | $13.50/1M from $8.28 at Kenari | -3% | — |
 GLM-5.3Zhipu AI | $1.40/1M | $4.40/1M from $1.10 at NanoGPT | ±0% | — |
 Qwen3.8 2.4T A95BAlibaba | $2/1M | $6/1M from $4.11 at APIMart | ±0% | — |
| GLM-5.3-FlashZhipu AI | $0.15/1M | $0.50/1M from $0.20 at APIMart | ±0% | — |
| GLM-5.2Zhipu AI | $1.30/1M | $4.09/1M from $1.80 at Deep Infra | -7% | — |
| GPT OSS 120BOpenAI | $0.05/1M | $0.45/1M from $0.14 at Requesty | +221% | — |
 MiniMax-M3MiniMax | $0.30/1M | $1.20/1M from $0.90 at EmpirioLabs AI | ±0% | — |
| GLM-5Zhipu AI | $0.95/1M | $2.55/1M from $1.28 at APIMart | -20% | — |
| Kimi K2.5Moonshot AI | $0.45/1M | $2.25/1M from $0.555 at APIMart | +305% | — |
| Qwen3.5 9BAlibaba | $0.10/1M | $0.15/1M from $0.13 at EmpirioLabs AI | +15% | — |
| GPT OSS 20BOpenAI | $0.04/1M | $0.18/1M from $0.09 at OpenRouter | +100% | — |
| Qwen3 8BAlibabaCheapest | $0.06/1M | $0.06/1M | — | — |
| Qwen3.6 35B-A3BAlibaba | $0.24/1M | $1.80/1M from $0.95 at Deep Infra | -20% | — |
| Kimi K2.6Moonshot AI | $0.77/1M | $3.40/1M from $2.40 at APIYI | -9% | — |
| GLM-5.1Zhipu AI | $1.19/1M | $3.74/1M from $1.44 at APIMart | -15% | — |
| GLM-4.7Zhipu AI | $0.42/1M | $2.20/1M from $1.10 at AIHubMix | ±0% | — |
 Gemma 4Google | $0.75/1M | $1/1M from $0.30 at FastRouter | +233% | — |
| Qwen3-VL-8B-InstructAlibaba | $0.18/1M | $0.68/1M from $0.278 at SiliconFlow | +145% | — |
| Kimi K2.7 Code HighSpeedMoonshot AI | $0.859/1M | $3.80/1M from $2.76 at Kenari | +1% | — |
| Qwen3.6 27BAlibaba | $0.30/1M | $3.20/1M from $2 at OpenRouter | -11% | — |
| LongCat-2.0Meituan | $0.75/1M | $2.95/1M from $1.20 at Atlas Cloud | +146% | — |
| Qwen3 14BAlibaba | $0.07/1M | $0.28/1M from $0.20 at Hugging Face | +40% | — |
| Qwen2.5-7B-InstructAlibabaCheapest | $0.05/1M | $0.05/1M | — | — |
| Qwen3 Coder 480B A35B InstructAlibaba | $0.25/1M | $1/1M from $0.95 at Helicone | +5% | — |
| Qwen3-Coder 30B-A3B InstructAlibaba | $0.07/1M | $0.28/1M from $0.27 at DevPass (LLM Gateway) | +4% | — |
| Qwen3.5 35B-A3BAlibaba | $0.24/1M | $1.80/1M from $0.451 at AIHubMix | -10% | — |
| GLM-4.5-AirZhipu AI | $0.14/1M | $0.86/1M from $0.291 at ZenMux | -22% | — |
| Gemma 4 26B A4B ITGoogle | $0.14/1M | $0.40/1M from $0.225 at OpenRouter | -33% | — |
| Qwen3 32BAlibaba | $0.14/1M | $0.57/1M from $0.25 at Hugging Face | +128% | — |
| Qwen3.5 27BAlibaba | $0.25/1M | $2/1M from $0.677 at AIHubMix | -17% | — |
| Gemma 4 12B InstructGoogleOnly here | $0.10/1M | $0.30/1M | — | — |
 Hunyuan-A13B-InstructTencent | $0.14/1M | $0.57/1M from $0.556 at SiliconFlow | +3% | — |
 Deepseek 3.2DeepSeek | $0.27/1M | $0.42/1M from $0.308 at APIMart | +36% | — |
| DeepSeek R1 0528DeepSeek | $0.50/1M | $2.18/1M from $1.23 at APIMart | +77% | — |
| DeepSeek V3 0324DeepSeek | $0.25/1M | $1/1M from $0.822 at APIMart | +22% | — |
| DeepSeek V3.1 TerminusDeepSeek | $0.27/1M | $1/1M from $0.95 at Hugging Face | +5% | — |
| DeepSeek V4 Flash Vision ExpDeepSeek | $0.44/1M | $1.32/1M from $0.48 at CometAPI | +175% | — |
| DeepSeek-V3.1DeepSeek | $0.27/1M | $1/1M from $0.798 at Poe | +25% | — |
| DeepSeek-V3.2-ExpDeepSeek | $0.27/1M | $0.41/1M from $0.308 at APIMart | +33% | — |
| GLM-5V-TurboZhipu AI | $1.20/1M | $4/1M from $3.10 at AIHubMix | +29% | — |
| Hy3Tencent | $0.132/1M | $0.528/1M from $0.33 at OpenRouter | +60% | — |
| Hy4 previewTencent | $0.834/1M | $2.50/1M from $2.25 at OpenRouter | +11% | — |
 Ling-flash-2.0Inclusionai | $0.14/1M | $0.57/1M from $0.544 at AIHubMix | +5% | — |
| Qwen2.5-72B-InstructAlibaba | $0.59/1M | $0.59/1M from $0.40 at Deep Infra | +48% | — |
| Qwen3 30B-A3B Instruct 2507Alibaba | $0.09/1M | $0.30/1M from $0.30 at Cortecs | ±0% | — |
| Qwen3.5 122B-A10BAlibaba | $0.26/1M | $2.08/1M from $0.901 at AIHubMix | -35% | — |
 Seed Oss 36B InstructByteDance | $0.21/1M | $0.57/1M from $0.534 at AIHubMix | +7% | — |
 Step 3.5 FlashStepFun | $0.10/1M | $0.30/1M from $0.292 at SiliconFlow | +3% | — |
SiliconFlow at a glance
48 models in total: 48 text. The cheapest is Qwen2.5-7B-Instruct at $0.05 /1M. LongCat-2.0 has the largest context window, 1.05M tokens. The most searched is Kimi K3, with about 658K Google searches a month. The newest is DeepSeek V4 Flash Vision Exp, released Aug 31, 2026.
Cheapest
- Qwen2.5-7B-Instruct$0.05/1M
- Qwen3 8B$0.06/1M
- Qwen3.5 9B$0.15/1M
- GPT OSS 20B$0.18/1M
- Qwen3 14B$0.28/1M
Largest context
- LongCat-2.01.05M
- Kimi K31.05M
- GLM-5.31.05M
- GLM-5.3-Flash1.05M
- DeepSeek V4 Flash Vision Exp1.05M
Most searched
- Kimi K3658K
- GLM-5.3276K
- Qwen3.8 2.4T A95B234K
- GLM-5.3-Flash121K
- GLM-5.2109K
Newest
- DeepSeek V4 Flash Vision ExpAug 31, 2026
- Hy4 previewAug 27, 2026
- GLM-5.3Aug 25, 2026
- GLM-5.3-FlashAug 25, 2026
- Qwen3.8 2.4T A95BAug 8, 2026