Fugu Ultra

sakana/fugu-ultra

Quality-first multi-agent model for hard research, analysis, and competitions

Compare

Context window: 1M
Input: Text · Image
Output: Text
Released: 2026-06-15

Max output: 128K
Weights: Closed
Capabilities: Attachments, Reasoning, Tool call, Structured

Pricing

No official pricing available.

Estimate usage cost

Compare verified public prices for this exact model and region. Enter uncached input and cache usage separately. Estimates exclude unspecified fees, credits and currency conversion. Set requests to zero to estimate token charges only.

Input tokens

Output tokens

Cache read tokens

Cache write tokens

Requests

Context tokens (optional)

Currency

Batch processing

Performance


SWE Bench Pro	Coding	Scale AI	2026-08-05
Terminal Bench 2.1	Coding	Terminal-Bench	2026-08-05
LiveCodeBench	Coding	LiveCodeBench	2026-08-05
LiveCodeBench Pro	Coding	LiveCodeBench Pro	2026-08-05
Humanity’s Last Exam	Knowledge & language	Center for AI Safety / Scale AI	2026-08-05
CharXiv Reasoning	Reasoning	Princeton NLP	2026-08-05
GPQA Diamond	Reasoning	Scale	2026-08-05
SciCode	Coding	SciCode	2026-08-05

Providers

							Cache write
OpenRouter	sakana/fugu-ultra	Openai chat	global				-

ModelRegistry · Catalog updated 2026-09-29