Sakana AI
Fugu Ultra
Quality-first multi-agent model for hard research, analysis, and competitions
sakana/fugu-ultra
Context
1M
Output
—
Released
2026-06-15
Knowledge cutoff
—
Types
InputTextImage
OutputText
Reasoning
Supported
Tool use
Supported
Structured output
Supported
Attachments
Supported
Open weights
—
Provider pricing
CommandCode
InTextImage
OutText
- Price
- $5.00 / $30.00
- Context
- 1M
- Status
- Stable
Kilo Gateway
InTextImage
OutText
- Price
- $5.00 / $30.00
- Context
- 1M
- Status
- Stable
LLM Gateway
InTextImage
OutText
- Price
- $5.00 / $30.00
- Context
- 1M
- Status
- Stable
LLMTR
InTextImage
OutText
- Price
- $5.00 / $30.00
- Context
- 1M
- Status
- Stable
Merge Gateway
InTextImage
OutText
- Price
- $5.00 / $30.00
- Context
- 1M
- Status
- Stable
NanoGPT
InTextImage
OutText
- Price
- $5.00 / $30.00
- Context
- 1M
- Status
- Stable
OpenRouter
InTextImage
OutText
- Price
- $5.00 / $30.00
- Context
- 1M
- Status
- Stable
Pioneer
InTextImage
OutText
- Price
- $5.00 / $30.00
- Context
- 1M
- Status
- Stable
Vercel AI Gateway
InTextImage
OutText
- Price
- $5.00 / $30.00
- Context
- 1M
- Status
- Stable
AI/ML API
InTextImage
OutText
- Price
- $6.88 / $41.26
- Context
- 1M
- Status
- Stable
Benchmarks
SWE Bench Pro
73.7
Terminal Bench 2.1
82.1
LiveCodeBench
93.2
LiveCodeBench Pro
90.8
Humanity’s Last Exam
50
CharXiv Reasoning
86.6
GPQA Diamond
95.5
SciCode
58.7
τ3 Banking
20.6
Long Context Reasoning
73.3
MRCRv2
93.6
CTI-REALM
69.4