Sakana Namazu

sakana/namazu

A chat model with a 256K-token context window, at $0.9975 per million input tokens and $4.20 per million output tokens.

Details

Maker: sakana
Kind: Chat
Context window: 256,000 tokens
Max output: 256,000 tokens
Input: $0.9975 per million tokens
Cached input: $0.1575 per million tokens, 84% off
Cache write: Same as input
Output: $4.20 per million tokens
Capabilities: Reasoning, tool use, vision, file input, web search
Takes: Text, image, pdf
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-08-03

Description

Sakana Namazu is a Japanese-specialized LLM that combines a deep understanding of Japanese culture and business customs with high-performance language capabilities. Built on the open model Kimi K2.6 and refined with Sakana AI's in-house data for Japanese language and business workflows, it handles complex tasks using web search and code execution. Unlike Fugu, which orchestrates multiple frontier models, Sakana Namazu provides a single in-house model as an API.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sakana/namazu",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model