Fugu Ultra v2 vs Sakana Namazu compared — price per token, context window, multimodality, openness and which to choose. Full 2026 breakdown.
Fugu Ultra v2 — full profile › · Sakana Namazu — full profile ›
Prices & specs refreshed from live data · olud.ai
Open-model prices = cheapest provider via OpenRouter; official maker rates may be higher.
| Spec | Fugu Ultra v2 | Sakana Namazu | Winner |
|---|---|---|---|
| Maker | Sakana AI | Sakana AI | – |
| Type | Proprietary | Proprietary | – |
| Context window | 1M tokens | 262K tokens | SAFugu Ultra v2 |
| Input price | $5/M | $0.95/M | SASakana Namazu |
| Output price | $30/M | $4/M | SASakana Namazu |
| Vision / multimodal | Yes | Yes | = Tie |
| Tool / function calling | Yes | Yes | = Tie |
| Self-hostable | No (API only) | No (API only) | – |
| License | Proprietary | Proprietary | – |
Sakana Namazu is ~7.5× cheaper than Fugu Ultra v2 on output tokens ($4 vs $30 per M tokens).
| Capability | Fugu Ultra v2 | Sakana Namazu |
|---|---|---|
| Open weights (downloadable) | ✗ | ✗ |
| Self-hostable | ✗ | ✗ |
| Runs fully offline | ✗ | ✗ |
| Vision / multimodal | ✓ | ✓ |
| Tool / function calling | ✓ | ✓ |
| 1M+ context window | ✓ | ✗ |
| Criterion | Fugu Ultra v2 | Sakana Namazu |
|---|---|---|
| Cost-efficiency | 3.0 | 4.0 |
| Context window | 5.0 | 4.0 |
| Openness | 1.5 | 1.5 |
| Self-hosting | 1.0 | 1.0 |
| Multimodality | 5.0 | 5.0 |
Scores come from live data — output price (cost), context length, open vs closed weights (openness & self-hosting) and vision/tool support (multimodality). Raw task quality isn't scored here; it depends on your benchmark — see the verdict.
Fugu Ultra v2 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...
Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...
Sakana Namazu is cheaper on output ($4/M vs $30/M).
Fugu Ultra v2 offers the larger context window (1M tokens).
Choose Sakana Namazu for the lower output price ($4/M vs $30/M). Choose Fugu Ultra v2 if you need the larger 1M context window.
Browse the full open-source model leaderboard, thousands of tools and live benchmarks — all in one place.
Open the leaderboard →