Fugu Ultra v2
Fugu Ultra v2 is a large language model made by Sakana, added to the catalog on 11 Sep 2026. It has a context window of 1,000,000 tokens and costs $5.00 per 1M input tokens and $30.00 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: working with long documents, answering questions about provided images and files and producing structured text.
Price checked ยท source: OpenRouter
What Fugu Ultra v2 is
Sakana: Fugu Ultra v2 is a text-producing model from Sakana AI and a member of the Fugu family. The catalog describes Fugu as a learned multi-agent orchestration system involving a language model, rather than a single monolithic model. The available description does not provide further details about how that orchestration works. Fugu Ultra v2 accepts text, images, and files, and returns text.
Its context window is 1,000,000 tokens, and its maximum output is 128,000 tokens. This capacity suits requests that include extensive context, such as reviewing long documents or referring to multiple pieces of supplied material in one conversation. The catalog does not specify supported file formats or detail how images are interpreted, so those capabilities should not be assumed beyond the listed input types.
The model supports tools, structured outputs, reasoning, and web search options. These options are relevant to workflows involving tool use, responses organized into a defined structure, or tasks that call for reasoning. Web search options may be useful in research workflows when available in the interface. The catalog does not name particular tools, schemas, or search behavior, and it does not describe a specialized domain. Fugu Ultra v2 is therefore described here by its listed input and output types, context limits, and supported options rather than by claims about specific outcomes.
Key features
- Accepts text, images, and files
- Produces text
- Has a 1,000,000-token context window
- Supports up to 128,000 output tokens
- Supports tools, structured outputs, reasoning, and web search options
Typical uses
- Working with long documents
- Answering questions about provided images and files
- Producing structured text
- Reasoning through written questions
- Research workflows using web search options
Fugu Ultra v2 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $5.00 |
| Output, per 1M tokens | $30.00 |
| Cached input read, per 1M tokens | $0.50 |
| Web search, per search | $0.01 |
| Input above 272,000 prompt tokens, per 1M | $10.00 |
| Output above 272,000 prompt tokens, per 1M | $45.00 |
No price change since it was added on 11 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.012 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.149 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.210 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.795 |
Fugu Ultra v2 specifications
| Model id | sakana/fugu-ultra-v2 |
|---|---|
| Version | fugu-ultra-v2-20260911 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | 2026-08-28 |
| Added to catalog | 11 Sep 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 Fugu Ultra v2 yet.
Compare Fugu Ultra v2
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.