{"type":"analysis","id":"analysis:research-deepseek-open-sourced-deepinfer-for-v4-1-flash-but-the-compute-crunch-figures","slug":"research-deepseek-open-sourced-deepinfer-for-v4-1-flash-but-the-compute-crunch-figures","title":"DeepSeek open-sourced DeepInfer for V4.1-Flash, but the compute-crunch figures attached to it are unverified","description":"DeepSeek's production inference engine is now on GitHub under Apache-2.0, aimed at Blackwell-class NVIDIA GPUs and Huawei Ascend 950. The GPU-economics claims that travelled with the news come from an SF Compute opinion post; public trackers back its B300 rental price, not its revenue or upfront-payment figures.","published_at":"2026-11-08T21:00:00.000Z","updated_at":"2026-11-08T21:00:00.000Z","record_date":"2026-11-08","topics":["github","research"],"source_urls":["https://github.com/deepseek-ai/DeepInfer","https://github.com/deepseek-ai/DeepInfer/blob/main/README.md","https://github.com/deepseek-ai/DeepInfer/blob/main/examples/README.md","https://github.com/gpustack/DeepInfer-server","https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash","https://gpurentalprices.com/","https://www.priceofcompute.com/gpus/b300","https://gpueconomy.com/gpu/b300","https://api-docs.deepseek.com/quick_start/pricing","https://evanjconrad.com/posts/end-of-startups"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-deepseek-open-sourced-deepinfer-for-v4-1-flash-but-the-compute-crunch-figures/","markdown":"https://newruntime.com/analysis/research-deepseek-open-sourced-deepinfer-for-v4-1-flash-but-the-compute-crunch-figures.md","json":"https://newruntime.com/analysis/research-deepseek-open-sourced-deepinfer-for-v4-1-flash-but-the-compute-crunch-figures.json"},"author":{"role":"author","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:6af3013c-a991-4105-91bc-f69b9988e451","authorial_article_id":"6af3013c-a991-4105-91bc-f69b9988e451"},"next_reads":[{"type":"topic","path":"/topics/github/","url":"https://newruntime.com/topics/github/","title":"Github","reason":"Explore the github topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/github.md","json_url":"https://newruntime.com/topics/github.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}