APOLLO11 Launches EdgeLLM On-Premise AI With Published Pricing
APOLLO11 is positioning EdgeLLM as a third path between cloud API use and self-built LLM infrastructure, giving regulated organizations a price-published on-premise option that addresses the shadow AI problem.
Reporting from 1 source: ASCII.jp.
APOLLO11 began offering EdgeLLM on August 31, an on-premise generative AI platform that keeps inference data inside the customer's network. The company published a package price starting at 9.8 million yen, with no usage-based billing. It targets law firms, medical institutions, and government offices that cannot send confidential data to external servers. Standard implementation takes five to six weeks. APOLLO11 aims for 10 deployments in 2026.
EdgeLLM runs inside the customer's LAN and exposes an OpenAI-compatible API endpoint, so existing integration code and frameworks such as LangChain carry over without rewriting. APOLLO11 says the standard LAN-only configuration avoids third-party and cross-border transfer of personal data, which it ties to Japan's Act on the Protection of Personal Information.
The company targets lawyers bound by attorney confidentiality rules, medical institutions under patient-data rules, and government offices whose security policies ban external cloud AI. It also frames the product as an answer to shadow AI, the practice of staff quietly using personal accounts for external AI tools. APOLLO11 aims for 10 deployments in 2026 and plans quarterly model updates.
Synthesized by Yomimono from the 1 cited source below, including Japanese-language reporting where cited, then editorially reviewed before publishing.