SiliconFlow Models — Pricing & Benchmarks
12 models available
Last refreshed 2026-10-26. Next refresh: weekly.
SiliconFlow hosts 12 AI models in this catalog. The lowest listed input price is Qwen2.5-7B-Instruct at $0.05/1M input tokens. 1 retired model is listed below. LLM Reference compares these models across all 137 providers.
Available models(12)
Retired models(1)
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
Mistral Large 2 (2407)Deprecated | $2.00 | $2.00 | 128K |
Where else to run this
Grok-2 on SiliconFlow
Provider setup and pricing
Mixtral 8x7B on SiliconFlow
Provider setup and pricing
DeepSeek R1 on SiliconFlow
Provider setup and pricing
Mixtral 8x7B on Databricks Foundation Model Serving
Alternative host
DeepSeek R1 on DeepSeek Platform
Alternative host
DeepSeek V3 on DeepInfra
Alternative host
Pricing Overview
Cheapest$0.05/1M
Most expensive$0.65/1M