ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

Fugu Ultra

by Sakana AI

Current flagship mid tier

Today's price · per 1M tokens

Input

$5.00

per 1M tokens

Output

$30.00

per 1M tokens

Blended

$11.25

blended $/1M — 3:1 weighted input:output

Cached input

$0.500

10% of input — prompt caching

Source: official Sakana AI pricing · read Aug 7, 2026 MODELPRICEWATCH.COM · 2026-08-09

Overview

Sakana AI's frontier orchestration model — a multi-agent system served as a single OpenAI-compatible model that routes each request across a pool of expert LLMs, including recursive calls to itself. Pricing is context-tiered rather than flat: $5.00/$30.00 per 1M tokens at or below 272K context with cached input at $0.50, rising to $10 / $45 / $1.00 above 272K. One fixed rate covers both fugu-ultra-v1.1 and fugu-ultra-v1.0.

Capabilities

struck through = not supported
Input 2/5
Text ✓ Image ✓ Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 4/9
Prompt caching ✓ Reasoning ✓ Coding Fast inference Long context ✓ Open weights Multimodal ✓ Web search Realtime

Specifications

Provider
Sakana AI
Context window
1M tokens
Modality
text, image
Parameters
Proprietary
Open source
No — proprietary
Released
Jun 22, 2026
Status
Current
Last updated
Aug 7, 2026
Tags
flagshipreasoningagenticcachingmultimodal

Availability verified: Aug 7, 2026 — listed on Sakana AI's own page