Sakana Namazu

Sakana Namazu is a Japanese-specialized reasoning model based on Kimi K2.6, tuned for Japanese language, culture, and business workflows. It is the first version in the sakana-namazu line. It has a context window of 262144 tokens and a maximum output of 65536 tokens. Pricing starts at $0.95 per million input tokens and $4.00 per million output tokens, with cached input at $0.15 per million tokens. The weights are not open. It supports reasoning mode and tool calling, and accepts image, PDF, and text inputs, returning text.

First version of its line in the registry.

• ·Japanese-specialized reasoning tuned for business workflows
• ·262144 token context window
• ·65536 token max output
• ·Supports tool calling and reasoning mode
• ·Accepts image, PDF, and text inputs

• Reach for it for Japanese language reasoning tasks
• Reach for it for business workflows in Japanese
• Reach for it for long-context analysis
• Reach for it for processing mixed-media documents

5 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window size?

The context window is 262144 tokens.

Is the model open weights?

No, the weights are not open.

What input formats does it accept?

It accepts image, PDF, and text inputs.