sakana
Sakana: Fugu Max
sakana/fugu-max
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter's catalog describes sakana/fugu-max as Sakana AI's cost-performance entry in the Fugu family and as part of a learned multi-agent orchestration system rather than a standalone monolithic model. The listing reports text, image, and file inputs with text output, a one-million-token context window, mandatory reasoning that defaults to high effort, and support for tools, structured outputs, and web-search options. These are source-reported capabilities; no independent model card or measured benchmark results were included in this source pack.[1]
Strengths
- Catalog-reported multimodal input covers text, images, and files, with text-only output.[1]
- The listing reports a one-million-token context window, potentially useful for long prompts.[1]
- Mandatory reasoning defaults to high effort, with max and xhigh also listed; tools, structured outputs, and web-search options are supported.[1]
Limitations
- Only OpenRouter catalog data was supplied; an independent model card was not available in this source pack.[1]
- No benchmark measurements were included, so accuracy, latency, reliability, and the claimed cost-performance balance require workload validation.[1]
- The knowledge cutoff is not reported, and reasoning is mandatory with no listed low-effort option.[1]
Where to use it
Sources
- [1] OpenRouter catalog · Sakana: Fugu MaxSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Fugu Max is the cost-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-max
- Canonical ID
- sakana/fugu-max-20260911
- Creator
- sakana
- Added to OpenRouter
- 11.09.2026
- Context length
- 1,000,000
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $2 / out $6
- 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 high · 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 high · efforts: max, xhigh, high · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| 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 | $2 | $6 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.