Atlas / Models / Sakana / Sakana: Namazu

Sakana: Namazu✓ Catalog verified

sakana/namazu

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,...

Input price
$0.95 /1M
Output price
$4.00 /1M
Context
262K
Modalities
textimagefile
Released
Aug 11, 2026
Tool calling
✓ Yes
Atlas signal
88/100
01

Overview

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,...

Access: available through the official Sakana API. Context window: 262K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 11, 2026
02

Specifications

API identifiersakana/namazu
ProviderSakana
Model typeMultimodal LLM
Context window262K catalog
Input modalitiestext · image · file
Output modalitiestext
ReleasedAug 11, 2026
ModeratedNo
Architecture modalitytext+image+file->text
Supported parameters
include_reasoningreasoningreasoning_effortstructured_outputstool_choicetoolsweb_search_options
Source: provider documentation + catalog feedMethodology →
03

Pricing

Live pricing components for sakana/namazu as published in the catalog.

$0.95
Input /1M
$4.00
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$9.5e-7$0.95 / 1MPer input token
Completion tokens$0.000004$4.00 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search fee$0.007$0.007000Per search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$1.27Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual Understanding✓ SupportedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Sakana: Namazu
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
88signal
Math Signal (GSM8K proxy)
83signal
Science Signal (GPQA proxy)
83signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Sakana: Namazu through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="sakana/namazu",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Sakana: Namazu cost?

$0.95 per 1M input tokens and $4.00 per 1M output tokens on the official Sakana API.

What is the context window of Sakana: Namazu?

Sakana: Namazu supports up to 262K tokens of context.

Does Sakana: Namazu support tool / function calling?

Yes, Sakana: Namazu supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Sakana: Namazu?

Use the official Sakana API with the model id `sakana/namazu`. See the Quick start section above for code examples.