Fugu Ultra v2
As of Nov 22, 2026, the cheapest Fugu Ultra v2 API price is $5 per 1M input tokens (Kilo Gateway) and $30 per 1M output tokens (Kilo Gateway). Fugu Ultra v2 is offered by 4 providers in the fugu-ultra family, reasoning enabled.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.
| Kilo Gatewaysakana/fugu-ultra-v2 | Cheapest$5 | Cheapest$30 | $0.5 | — | 1.0M | 3d agoout −33.3% |
| OpenRoutersakana/fugu-ultra-v2 | †$5 | $30 | $0.5 | — | 1.0M | — |
| Vercel AI Gatewaysakana/fugu-ultra-v2 | †$5 | $30 | $0.5 | — | 1.0M | — |
| AI/ML APIsakana/fugu-ultra-v2 | $5.29 | $31.74 | $0.529 | — | 1.0M | 30d agoout −23.1% |
Fugu Ultra v2 price history
Output price per 1M tokens since tracking began on Sep 12, 2026, for the 2 providers whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| Kilo Gateway | $10 → $5 | $45 → $30 | −33.3% | |
| Kilo Gateway | $5 → $10 | $30 → $45 | +50% | |
| AI/ML API | $6.877 → $5.29 | $41.262 → $31.74 | −23.1% |
Fugu Ultra v2 pricing FAQ
What is the cheapest Fugu Ultra v2 API?
As of Nov 22, 2026, Kilo Gateway has the lowest Fugu Ultra v2 output price at $30 per 1M tokens, and Kilo Gateway has the lowest input price at $5 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Fugu Ultra v2?
4 providers list Fugu Ultra v2 on Sovyron; 4 of them sell it at a metered per-token price.
Is Fugu Ultra v2 free?
No provider in the Sovyron catalog lists a free tier for Fugu Ultra v2.
What is the context window of Fugu Ultra v2?
Fugu Ultra v2 supports a 1.0M-token context window and up to 1.0M output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—