Fugu Max
As of Nov 22, 2026, the cheapest Fugu Max API price is $2 per 1M input tokens (EmpirioLabs AI) and $6 per 1M output tokens (EmpirioLabs AI). Fugu Max is offered by 9 providers in the fugu-max 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. Seeing a wide range? Why the same LLM costs different amounts.
| EmpirioLabs AIfugu-max | Cheapest$2 | Cheapest$6 | $0.25 | — | 1.0M | — |
| Kilo Gatewaysakana/fugu-max | $2 | $6 | $0.25 | — | 1.0M | — |
| DevPass (LLM Gateway)fugu-max | $2 | $6 | $0.25 | — | 1.0M | — |
| LLM Gatewaysakana/fugu-max | $2 | $6 | $0.25 | — | 1.0M | — |
| Merge Gatewaysakana/fugu-max | $2 | $6 | $0.25 | — | 1.0M | — |
| NanoGPTsakana/fugu-max | $2 | $6 | $0.25 | — | 1.0M | — |
| OpenRoutersakana/fugu-max | $2 | $6 | $0.25 | — | 1.0M | — |
| Vercel AI Gatewaysakana/fugu-max | $2 | $6 | $0.25 | — | 1.0M | — |
| AI/ML APIsakana/fugu-max | $2.116 | $6.348 | $0.2645 | — | 1.0M | 30d agoout −23.1% |
Fugu Max price history
Output price per 1M tokens since tracking began on Oct 13, 2026, for the one provider whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| AI/ML API | $2.7508 → $2.116 | $8.2524 → $6.348 | −23.1% |
Fugu Max pricing FAQ
What is the cheapest Fugu Max API?
As of Nov 22, 2026, EmpirioLabs AI has the lowest Fugu Max output price at $6 per 1M tokens, and EmpirioLabs AI has the lowest input price at $2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Fugu Max?
9 providers list Fugu Max on Sovyron; 9 of them sell it at a metered per-token price.
Is Fugu Max free?
No provider in the Sovyron catalog lists a free tier for Fugu Max.
What is the context window of Fugu Max?
Fugu Max 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
—