sakana
Sakana: Fugu Ultra
sakana/fugu-ultra
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter's catalog presents Sakana: Fugu Ultra as the higher-performance member of Sakana AI's Fugu family, described as a learned multi-agent orchestration system rather than a single monolithic model. The catalog lists text and image inputs, text output, a one-million-token context window, and mandatory reasoning with several high effort settings. It also advertises tool calls, structured outputs, and web search options. No measured benchmark results or independent model card were supplied.[1]
Strengths
- The catalog lists text and image inputs, text-only output, and a one-million-token context window.[1]
- It describes the system as learned multi-agent orchestration, with mandatory reasoning and several high effort settings.[1]
- Supported parameters include tools and tool choice, structured outputs, reasoning controls, and web search options.[1]
Limitations
- All evidence comes from OpenRouter's catalog; an independent model card was not available in this source pack.[1]
- The supplied benchmark fields were empty or unavailable, so measured quality remains unverified here.[1]
- The catalog does not state a knowledge cutoff, and the model still needs validation on the intended workload.[1]
Where to use it
Sources
- [1] OpenRouter catalog · Sakana: Fugu UltraSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
Specifications
- Model ID
- sakana/fugu-ultra
- Canonical ID
- sakana/fugu-ultra-20260615
- Creator
- sakana
- Added to OpenRouter
- 24.06.2026
- Context length
- 1,000,000
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $5 / out $30
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: mandatory · default xhigh · efforts: max, xhigh, high · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default xhigh · efforts: max, xhigh, high · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Sakana AI | 1,000,000 | $5 | $30 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.