Multi-agent model for routing expert agents across complex analytical tasks
Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.
| Provider | Provider model ID | Context | Max output | Input | Output | Cache read | Capabilities | Docs |
|---|---|---|---|---|---|---|---|---|
fugu |
1M | 1M | — | — | — | ReasoningToolsJSON | Docs ↗ |
Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.
Recorded from the source catalog and provider listings.
sakana/fuguEvery result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
Each axis is this model's percentile among the 3 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.
Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.
Listed input price plotted against GPQA Diamond, the benchmark with the widest published coverage that this model appears in.
The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.
Field-level changes detected between successful source imports.
This record has not changed within the retained import history.
Every figure on this page traces back to one of these records.
Fetch the complete source-linked model record. No key, no account, no rate-limited tier.
GET https://modelbench.lol/api/v1/models/sakana/fugucurl "https://modelbench.lol/api/v1/models/sakana/fugu"Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.
Multi-agent model for routing expert agents across complex analytical tasks. It is published by Sakana and catalogued here from Models.dev.
Fugu accepts up to 1M tokens of context.
Provider catalogs list support for tool calling, structured output, reasoning, and image input.
1 provider list this model: Sakana AI.
No. This model is served through hosted APIs only.
The catalog records a release date of 2026-06-15, last verified Oct 24, 2026.
Quality-first multi-agent model for hard research, analysis, and competitions
Sakana NamazuJapanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows
Fugu Ultra v2Quality-first multi-agent model for hard research, analysis, and competitions
Fugu MaxMulti-agent model for routing expert agents across complex analytical tasks