DeepSeek's October 2026 open-sourcing of its DeepInfer model-serving software could make DeepSeek's AI models cheaper for businesses to run, according to Bloomberg

On October 20, 2026 DeepSeek open-sourced DeepInfer, the in-house inference framework it uses to serve its models, under the Apache 2.0 license; at release it supported only DeepSeek-V4.1-Flash on Nvidia SM100 GPUs and Huawei Ascend 950 chips.