Sakana AI Opens Namazu API to Developers Building Japanese Enterprise Apps
Sakana AI opens its Japanese-specialized Namazu LLM as an API, built on Kimi K2.6 with Japan-specific fine-tuning, built-in web search, and OpenAI-compatible endpoints.
- Sakana Namazu API is live -- Sakana AI's Japanese-specialized LLM is now available via API at console.sakana.ai
- Built on Kimi K2.6 -- fine-tuned with proprietary data for Japanese language and business contexts, not trained from scratch
- Beats base model on Japan-specific benchmarks -- FairPoliticsQA score jumped from 34.10% to 56.30%; outperforms K2.6 on JFBench and translation
- Web search and code execution built in -- no extra scaffolding needed for agentic workflows
- Drop-in OpenAI replacement -- change
base_urland API key, existing code works unchanged - Enterprise-focused -- targets the gap between costly frontier models and raw open-weight models for Japanese business use
Sakana Namazu is now available as a commercial API. The Tokyo-based lab behind it has been running Namazu inside its Sakana Chat product for months, and the consistent feedback was simple: people wanted to call it from their own code. Today, that is possible. The model is live at console.sakana.ai, and if you already have an OpenAI-compatible client, switching over is a two-line change.
What Namazu actually is
Namazu is not trained from scratch. It is built on Kimi K2.6, the open model published by Moonshot AI. Using Sakana's own in-house data, the team adapted the model to Japanese and to Japanese business contexts, and also tuned it to reduce unnecessary refusals on certain topics and to limit bias in its outputs. Think of it as a targeted fine-tune of an already strong open-weight base, aimed squarely at the Japanese enterprise market.
Kimi K2.6 is a general-purpose model with stable long-horizon coding, instruction-following, and self-correction capabilities. It supports text, image, and video input, thinking and non-thinking modes, and dialogue and agent tasks. Sakana's fine-tuning preserves those strengths while layering on Japanese fluency and cultural context that the base model lacks.
The gap it fills
The Japanese enterprise LLM market has a real problem. Frontier models are costly, and using an open model as-is leaves open questions about quality and about how data is handled. Namazu is positioned as the middle path: a model that has been adapted to Japanese business workflows, served through a familiar API, at a price point below the frontier tier. Sakana AI is a Tokyo-based startup founded in 2023, whose co-founders include David Ha and Llion Jones, authors of the original Transformer paper "Attention Is All You Need."