Sakana Namazu
Sakana Namazu is a reasoning model developed by Sakana AI, specifically optimized for Japanese language and business contexts. It supports a large context window and can process text, images, and files to provide text-based responses.
Sakana Namazu specs and pricing
- Provider: Sakana
- Released: August 11, 2026
- Context window: 262K tokens
- Max output: 66K tokens
- Input: text, images, files
- Output: text
- Price: $0.95 input / $4.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Sakana Namazu is good at
- Complex reasoning tasks in Japanese
- Analyzing business documents and images
- Following intricate instructions in a professional setting
To-dos to try with Sakana Namazu
- Summarize the key points from this 50-page Japanese business report and extract all action items.
- Analyze the provided image of a handwritten Japanese meeting note and convert it into a structured text summary.
- Draft a formal Japanese email response based on the attached project proposal file.
FAQ
- What is Sakana Namazu primarily designed for? It is a reasoning model specialized in the Japanese language and business-related instruction following.
- Can this model process files and images? Yes, it supports input in text, image, and file formats.
- How much does Sakana Namazu cost? Sakana Namazu costs $0.95 per million input tokens and $4.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 3.22 credits ($1 = 100 credits).
- What is the context window of Sakana Namazu? Sakana Namazu can read up to 262K tokens at once and write up to 66K tokens in one reply.
- Can I use Sakana Namazu without coding? Yes. In todo.is you pick Sakana Namazu as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.