Name: Sakana Namazu API
Brand: Sakana AI

Overview

What is Sakana Namazu API?

Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following and business workflows, supports a 262K context window, and accepts text, image, and file inputs.

Technical Specifications
- Context window: 262,144 tokens
- Max output: 65,536 tokens
- Supported inputs: Image, Text
- Output: Text

Sakana Namazu API Pricing
- Input: $1.235 / 1M tokens
- Output: $5.2 / 1M tokens
- Cached input: $0.195 / 1M tokens

Use cases

Market research report generation is a documented use case for Sakana Namazu. Sakana AI says the model can autonomously handle the full workflow from planning the research, through repeated web searching and information cross-checking, to writing the report.

Customer support automation is another documented use case. Sakana AI describes using Sakana Namazu for Japanese-language inquiry handling, and also for analyzing order data in the same workflow.

Business writing and document work are documented use cases as well. Sakana AI says the model is refined for Japanese language and business workflows, and is suited to producing natural Japanese documents and materials for recurring daily office tasks.

Research and coding agents are also documented use cases. Sakana AI’s model listing says Sakana Namazu handles complex tasks using web search and code execution, and third-party documentation describes it as suited to research or coding agents that need to work naturally in Japanese.

How to use Sakana Namazu API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to sakana/sakana-namazu.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "sakana/sakana-namazu",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())

const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "sakana/sakana-namazu",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());

curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"sakana/sakana-namazu","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.