Sakana Namazu
Sakana Namazu is Sakana AI's Japanese-specialised model, adapted from an open base for Japanese business context and honorific speech, with a context window of 256K tokens and built-in tools.
View API reference- Input and output price
- Input $0.95, Output $4, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'sakana/namazu', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Sakana Namazu by Sakana AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Sakana Namazu
Sakana Namazu
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Sakana Namazu through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'sakana/namazu', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Sakana Namazu request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'sakana/namazu', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. sakana/namazu. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Sakana Namazu supports up to 256,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 256K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'sakana/namazu', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['sakana'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'sakana/namazu', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'sakana/namazu', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'sakana/namazu', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'sakana/namazu', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by Sakana AI
| Model |
|---|
| 1M | 3.8 s | $5/M+1 more | $30/M+1 more | Read$0.50/M | — | | 06/21/2026 |
Copy link to headingAbout Sakana Namazu
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.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: 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.
- Configuration: 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.
- Configuration: 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.
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Sakana Namazu
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 when
- 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
Copy link to headingConclusion
Sakana Namazu is a Japanese localisation of an open base model, tuned for business register, honorific speech, and fewer unnecessary refusals. Point sakana/namazu at AI Gateway when Japanese-language quality is the requirement, and check the regional restrictions before you deploy.
Copy link to headingFrequently 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.
Your use is subject to Sakana AI's Terms & Privacy Policies.