/ Models

Language models

Sakana: Fugu Ultra v2

Sakana · sakana/fugu-ultra-v2

Runs in the cloud, on our API — not on your own machine.

tools always reasons

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...

Install on 00

Get the 00 app

Free · macOS

Your agents, your models, your machine — this model installs with one click once the app is on board.

Download free →

What it costs

Input / 1M
$10
Output / 1M
$60
1M in + 1M out
$70
Cache read / 1M
$1
Web search / call
$0.02

Long prompts cost more

Prompt sizeIn / 1MOut / 1MCache read / 1M
Up to 272K$10$60$1
272K and above$20$90$2

The band follows the size of the prompt you send.

Final AI-token prices, per million tokens. Bring your own provider key in the app to pay provider rates directly.

What it can do

Takes
text, images and files
Returns
text
Tools
yes
Reasoning
always on
Context window
1M tokens
Max output
128K tokens
Open weights
no

Effort: max, xhigh and high — xhigh by default. More effort means more thinking tokens, billed at the output rate.

Dates

Released
2026-09-11
Knowledge cutoff
2026-08-28
Retires

Using it

In the 00 app — pick it per agent, and per tier, then build your own agents on it. Get 00.

As a drop-in API — the same model at an OpenAI-compatible endpoint. Two settings:

  1. Create a workspace API key in the Overblast console — usage bills that workspace's AI tokens, at the prices on this page.
  2. Point your base URL at https://brain.deployd.network/ai/v1. Chat completions with streaming, embeddings, /images, /audio/transcriptions and /videos.
curl https://brain.deployd.network/ai/v1/chat/completions \
  -H "Authorization: Bearer ob_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sakana/fugu-ultra-v2",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

← all models · compare it with another · calling image, video and speech models