Fugu Ultra

sakana/fugu-ultra

A chat model with a 1M-token context window, at $5.25 per million input tokens and $31.50 per million output tokens.

Details

Maker: sakana
Kind: Chat
Context window: 1,000,000 tokens
Max output: 1,000,000 tokens
Input: $5.25 per million tokens
Cached input: $0.525 per million tokens, 90% off
Cache write: Same as input
Output: $31.50 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: 2026-06-21
Newer model: sakana/fugu-maxReleased later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

Fugu Ultra coordinates a deeper pool of expert agents to maximize answer quality on hard, high-stakes problems. Fugu Ultra focuses on maximizing performance, for a higher cost. It routes between one to three agents, depending on the problem.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sakana/fugu-ultra",
    "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