| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Not measured | – |
| API surface | Identical contract to 1 other entry | api_956e60ef |
| Context and output | 1,000,000 context · 128,000 max output | declared |
| Reasoning contract | Mandatory · efforts max, xhigh, high · default xhigh | declared |
| Serving providers observed | Sakana AI | measured 3 September 2026 |
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 1261 prompt tokens.
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...
Supported parameters
include_reasoningreasoningreasoning_effortstructured_outputstool_choicetoolsweb_search_options
defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for Sakana: Fugu Ultra: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.
