# Sakana Namazu

Sakana AI's Japanese-specialised model. Sakana Namazu is a localisation of an open base model rather than a new pretrain, tuned on in-house data for Japanese business context, honorific register, and fewer unnecessary refusals.

- **Model ID:** `sakana/namazu`
- **Type:** chat
- **Providers:** sakana
- **Context window:** 256,000
- **Maximum output tokens:** 256,000
- **Pricing:** $0.95/1M input tokens, $4.00/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/namazu

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'sakana/namazu',
  prompt: 'Why is the sky blue?'
})
```

## About

Sakana Namazu is Sakana AI's Japanese-specialised model, exposed as an API on August 3, 2026. Sakana AI is explicit that it is a localisation of an existing open model rather than a new pretrain: the base is Kimi K2.6 from Moonshot AI, adapted with in-house data for Japanese and Japanese business contexts.

The adaptation targets three things. Japanese business register, including honorific speech, is the headline. Beyond that, Sakana AI tuned the model to reduce unnecessary refusals on ordinary topics and to limit bias in outputs, reporting a 22.2 point improvement on FairPoliticsQA over the base while broadly holding its performance on maths, general knowledge, and coding.

Capabilities cover image understanding, function and tool calling, structured JSON output, extended reasoning, web search, and streaming, within a context window of 256K tokens. Web search and code execution are available as built-in tools.

The API is OpenAI-compatible, so existing code often needs only a base URL change. Through AI Gateway you get that compatibility alongside unified billing and failover across providers.

You can integrate Sakana Namazu through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.

## What to consider

Regional availability is the first thing to check. Sakana Namazu is blocked in the EU and EEA, the United Kingdom, and Switzerland pending GDPR compliance, and Sakana AI states it cannot currently guarantee that data processing completes entirely within Japan. If either constraint touches your deployment, resolve it before you build.

Sakana Namazu is a localisation rather than a frontier pretrain. On general maths, knowledge, and coding it largely matches the Kimi K2.6 base rather than exceeding it, so the reason to choose it is Japanese-language quality and business register, not raw capability.

Sakana AI has since shipped a newer generation of the model and a separate orchestrator, Sakana Fugu, which coordinates multiple frontier models. Sakana Namazu works on its own as a single model, which is the simpler integration but not the strongest configuration Sakana AI offers.

## When to use

### Best For

- **Japanese business writing** where honorific register and formality have to be right
- **Japanese-market products** serving users who expect native-quality output
- **Reduced over-refusal** on ordinary topics where general models decline unnecessarily
- **OpenAI-compatible migration** that often needs only a base URL change
- **Tool-using Japanese agents** with built-in web search and code execution

### Consider Alternatives When

- **You operate in the EU, UK, or Switzerland**, where the model is currently blocked
- **Data residency in Japan** must be guaranteed, which Sakana AI cannot currently promise
- **General capability** is the priority, where the Kimi K2.6 base performs comparably outside Japanese
- **Multi-model orchestration** suits the task, where Sakana Fugu coordinates several frontier models

## Best for

- **Japanese Business Writing:** Honorific register and formality handled correctly
- **Japanese-Market Products:** Native-quality output for Japanese users
- **Reduced Over-Refusal:** Fewer unnecessary declines on ordinary topics
- **OpenAI-Compatible Migration:** Often only a base URL change
- **Tool-Using Japanese Agents:** Built-in web search and code execution

## Consider alternatives

- **EU, UK, Or Swiss Deployments:** The model is currently blocked in those regions
- **Guaranteed Japan Residency:** Processing location cannot currently be guaranteed
- **General Capability Needs:** The Kimi K2.6 base performs comparably outside Japanese
- **Multi-Model Orchestration:** Sakana Fugu coordinates several frontier models

## Frequently asked questions

### What is Sakana Namazu built for?

Japanese-language work, particularly Japanese business context and honorific speech. Sakana AI adapted it with in-house data for those settings.

### Is Sakana Namazu a new model from Sakana AI?

No, and Sakana AI says so directly. It is a localisation of Kimi K2.6, an open model from Moonshot AI, rather than a new pretrain.

### Where can I use Sakana Namazu?

Not in the EU or EEA, the United Kingdom, or Switzerland, where it is blocked pending GDPR compliance. Sakana AI also states it cannot currently guarantee that data processing completes entirely within Japan.

### How does Sakana Namazu compare to its base model?

It largely holds the base model's performance on maths, general knowledge, and coding, with gains concentrated in Japanese-language quality and a 22.2 point improvement on FairPoliticsQA.

### What is the context window for Sakana Namazu?

The context window is 256K tokens, with up to 256K tokens per response.

### What tools does Sakana Namazu support?

Function and tool calling, structured JSON output, extended reasoning, streaming, and image understanding, with web search and code execution available as built-in tools.

### How does Sakana Namazu differ from Sakana Fugu?

Sakana Namazu is a single in-house model that works on its own. Fugu is an orchestrator that coordinates multiple frontier models.

### Does Sakana Namazu support Zero Data Retention?

Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

## Links

- [Model page](https://vercel.com/ai-gateway/models/namazu)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://console.sakana.ai/models)
- [Provider pricing](https://console.sakana.ai/pricing#sakana-namazu)