LLM Reference

SiliconFlow Models — Pricing & Benchmarks

12 models available

SiliconFlow hosts 12 AI models in this catalog. The lowest listed input price is Qwen2.5-7B-Instruct at $0.04/1M input tokens. LLM Reference lets you compare these models across all 65 providers without switching tabs.

ModelInput (per 1M)Output (per 1M)Context
Qwen2.5-7B-Instruct$0.04$0.04128K
Qwen2.5-14B-Instruct$0.08$0.08128K
DeepSeek V3$0.15$0.564k
Qwen2.5-32B-Instruct$0.15$0.15128K
Qwen2.5-Coder-32B-Instruct$0.18$0.18128K
Mixtral 8x7B$0.2$0.232K
DeepSeek R1$0.25$0.8128K
Qwen2.5-72B-Instruct$0.28$0.28128K
Mistral NeMo (2407)$0.3$0.3128K
Grok-2$0.5$0.5128K
Mixtral 8x22B Instruct v0.1$0.65$0.6564K
Mistral Large 2 (2407)$2$2128K

Pricing Overview

Cheapest$0.04/1M
Most expensive$2.00/1M

About SiliconFlow

Full provider profile →