Sakana Namazu

Sakana AIMCP Tool CallReasoning

sakana/sakana-namazuClosed API

Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows

Benchmark Pricing$0.95 / 1M in$4.00 / 1M out$0.15 cache read

Context: 262,144 tokens•Max Output: 65,536 tokens•Released: 2026-08-03

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens

Max Output65,53665.5K tokens

LicenseProprietaryCloud API only

Input Modalities

TextVisionPDF

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Sakana Namazu natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

AIME26Unit not reported

96.67

MMLU-ProUnit not reported

90.33

LiveCodeBench v6Unit not reported

90.33

JFBenchUnit not reported

37.4

TranslationUnit not reported

52.2

FairPoliticsQAUnit not reported

56.3

API CALL INVOCATION EXAMPLE

// Example: Calling Sakana Namazu via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SAKANA_API_KEY,
});

const response = await client.chat.completions.create({
  model: "sakana/sakana-namazu",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);