DeepInfra
@DeepInfra
Fast ML inference. Run top AI models using a simple API.
๊ฐ์
February 2023
76 ํ๋ก์ ์ค 6K ํฌ
New on DeepInfra: Qwen3.8-2.4T-A95B ๐
@Alibaba_Qwen's latest sparse MoE โ 2.4T total params, 95B active, 512 experts. Built for coding, agentic workflows, and complex reasoning, with native 262K context.
Live now at $2.00/M in ยท $6.00/M out ยท $0.20/M cached
@Alibaba_Qwen @alibaba_cloud
๋ ๋ณด๊ธฐ
