Models / Sakana AI / Fugu Max

Sakana AI · fugu

Fugu Max

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

$2.00 in · $6.00 out

per 1M tokens · provider rate closest to the median. No first-party Sakana AI price was listed. The reference price is EmpirioLabs AI's rate, the provider closest to the median.

Provider input prices run from $2.00 to $2.75 per 1M tokens. Output prices run from $6.00 to $8.25.

Context
1,000,000
Max output
128,000
Cache read
$0.25
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Sep 11, 2026
Updated in source
Sep 11, 2026
Knowledge
—
Providers
7

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
EmpirioLabs AIreference$2.00$6.00$0.25——
Kilo Gateway$2.00$6.00$0.25——
Merge Gateway$2.00$6.00$0.25——
NanoGPT$2.00$6.00$0.25——
OpenRouter$2.00$6.00$0.25——
Vercel AI Gateway$2.00$6.00$0.25——
AI/ML API$2.75$8.25$0.34——