ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
5 models
Sakana
Sakana: Fugu Ultra v2 T
Reasoning Tools JSON

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

sakana/fugu-ultra-v2 2026-09-11 1M context $5/M input $30/M output
4 providers
Sakana: Fugu Max T
Reasoning Tools JSON

Multi-agent model for routing expert agents across complex analytical tasks

sakana/fugu-max 2026-09-11 1M context $2/M input $6/M output
9 providers
Sakana: Sakana Namazu T
Reasoning Tools JSON

Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows

sakana/sakana-namazu 2026-08-03 262.144K context $0.95/M input $4/M output
6 providers
Sakana: Fugu Ultra T
Reasoning Tools JSON

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

sakana/fugu-ultra 2026-06-15 1M context $5/M input $30/M output
14 providers
Sakana: Fugu T
Reasoning Tools JSON

Multi-agent model for routing expert agents across complex analytical tasks

sakana/fugu 2026-06-15 1M context Input not listed Output not listed
1 provider