Sakana Namazu

Tool callingStructured outputReasoningImage inputFile input

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

Context: 262K
Released: 2mo ago
Input / 1M tokens: $0.95
Output / 1M tokens: $4.00
Cached input / 1M tokens: $0.15

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Sakana
Model family: —
Type: Language model
Predecessor: —
Successor: —
Released: August 3, 2026
Model ID: sakana/sakana-namazu
Openness: Closed
License: —
Input modalities: text, image, file
Output modalities: text
Modality: text+image+file->text
Tokenizer: Other
Max output tokens: 66K
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: sakana/sakana-namazu
Source family: sakana-namazu
Last updated: 2026-08-03
Model context: 262K
Model output limit: 66K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature control: Yes

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
AIME26	96.67	—	Source
MMLU-Pro	90.33	—	Source
LiveCodeBench v6	90.33	—	Source
JFBench	37.4	—	Source
Translation	52.2	—	Source
FairPoliticsQA	56.3	—	Source

Official references

Complete source record (JSON)

{
  "id": "sakana/sakana-namazu",
  "name": "Sakana Namazu",
  "description": "Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows",
  "family": "sakana-namazu",
  "last_updated": "2026-08-03",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "pdf"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 262144,
    "output": 65536
  },
  "benchmarks": [
    {
      "name": "AIME26",
      "score": 96.67,
      "source": "https://console.sakana.ai/models?model=sakana-namazu"
    },
    {
      "name": "MMLU-Pro",
      "score": 90.33,
      "source": "https://console.sakana.ai/models?model=sakana-namazu"
    },
    {
      "name": "LiveCodeBench v6",
      "score": 90.33,
      "source": "https://console.sakana.ai/models?model=sakana-namazu"
    },
    {
      "name": "JFBench",
      "score": 37.4,
      "source": "https://console.sakana.ai/models?model=sakana-namazu"
    },
    {
      "name": "Translation",
      "score": 52.2,
      "source": "https://console.sakana.ai/models?model=sakana-namazu"
    },
    {
      "name": "FairPoliticsQA",
      "score": 56.3,
      "source": "https://console.sakana.ai/models?model=sakana-namazu"
    }
  ],
  "release_date": "2026-08-03",
  "open_weights": false,
  "links": [
    {
      "url": "https://sakana.ai/namazu/",
      "label": "Official product page",
      "type": "announcement"
    },
    {
      "url": "https://console.sakana.ai/models?model=sakana-namazu",
      "label": "Official model documentation",
      "type": "docs"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Sakana AI	sakana	262K	$0.95	$4.00	$0.15	—	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter