SiliconFlow
OpenAI-compatible API serving 200+ open-source LLM and multimodal models
SiliconFlow is an inference platform that serves open-source LLMs alongside image, video, and audio models through a single OpenAI-compatible API. It hosts 200+ models, including the DeepSeek, Qwen, and Kimi families, with per-token usage pricing and serverless deployment.
It also offers reserved GPU options for predictable billing. Developers use it as a drop-in alternative to other hosted inference APIs, switching by changing the base URL and key.
Pricing: Per token usage
SiliconFlow Alternatives
Explore 76 products in the Inference APIs category. View all SiliconFlow alternatives.
Lyceum
European GPU cloud for serverless inference, training, and on-demand GPU clusters
vLLM
High-throughput LLM inference engine with PagedAttention for efficient GPU memory usage
Work on SiliconFlow? Feature it at the top of Inference APIs.
Is your product missing?