Sakana Namazu
Sakana Namazu is a large language model made by Sakana, added to the catalog on 11 Aug 2026. It has a context window of 262,144 tokens and costs $0.95 per 1M input tokens and $4.00 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: japanese instruction following, japanese business document analysis and structured text generation.
Price checked ยท source: OpenRouter
What Sakana Namazu is
Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 and given additional training for Japanese language and business contexts. Its stated focus includes Japanese instruction following. It accepts text, images, and files, and produces text. This makes it suitable for requests that combine written instructions with supplied visual or file-based material, while keeping the response in text. The catalog lists reasoning as a supported capability, alongside tools, structured outputs, and web search options.
It has a context length of 262,144 tokens and a maximum output of 65,536 tokens. The context limit gives it room to consider extensive input within a single request, such as longer Japanese business documents or related material supplied as text or files. The output limit supports responses that need more than a brief answer, though the model's output remains text. Its Japanese and business focus makes it a fit for Japanese-language business instruction following, analysis of supplied material, and structured text generation. Tool support and web search options may be relevant when a task is configured to use those features; structured-output support is useful when a response needs a defined format. The catalog does not specify particular tools, file formats, or image-processing functions.
Key features
- Accepts text, image, and file inputs and produces text.
- Has a context length of 262,144 tokens.
- Supports reasoning, tools, structured outputs, and web search options.
- Has a maximum output of 65,536 tokens.
Typical uses
- Japanese instruction following
- Japanese business document analysis
- Structured text generation
- Reasoning over supplied text and files
Sakana Namazu pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.95 |
| Output, per 1M tokens | $4.00 |
| Cached input read, per 1M tokens | $0.15 |
| Web search, per search | $0.007 |
No price change since it was added on 11 Aug 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0017 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.027 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.037 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.149 |
Sakana Namazu specifications
| Model id | sakana/sakana-namazu |
|---|---|
| Version | namazu-20260811 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 65,536 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 11 Aug 2026 |
| Input types | text, image, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Sakana Namazu yet.
Compare Sakana Namazu
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.