Fugu Max

sakana/fugu-max

A chat model with a 1M-token context window, at $2.10 per million input tokens and $6.30 per million output tokens.

Details

Maker: sakana
Kind: Chat
Context window: 1,000,000 tokens
Max output: 1,000,000 tokens
Input: $2.10 per million tokens
Cached input: $0.2625 per million tokens, 88% off
Cache write: Same as input
Output: $6.30 per million tokens
Capabilities: Reasoning, tool use, vision
Takes: Text, image
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-09-10

Description

Fugu Max orchestrates our largest pool of models to push the cost–performance Pareto frontier. It dynamically finds efficient combinations of expert agents, aiming to improve model performance and cost efficiency together.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sakana/fugu-max",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model