fugu-ultra-v1.0-el · poe

Fugu Ultra v1.0 is Sakana AI's multi-agent conductor: it coordinates a pool of expert models on every request and composes their work into one answer, built for hard reasoning, coding, and research. It accepts text and image input with a 1M token context. Notes: - Responses can take from a few seconds to a few minutes to complete. - The full answer arrives at once rather than token by token (ie. streaming is not available), because the model finishes its internal work before it replies. - Extra High and Max reasoning levels are aliases. This bot supports optional parameters for additional customization.

Base model All models on this base All models of the provider to the provider

Input, $/1M $7.58

Output, $/1M $45.45

Cache read $1.52

Cache write —

Context 1 000 000

Accepts images, text

Last checked 04.11.2026 12:00:14 UTC

Source provider's page

Price alerts

API

OpenAI-compatible API: the official OpenAI SDKs work with this base URL. Replace YOUR_API_KEY with your key from the provider.

API base URL	`https://api.poe.com/v1`
Endpoint	`https://api.poe.com/v1/chat/completions`
Model id	`fugu-ultra-v1.0-el`

curl

curl https://api.poe.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "fugu-ultra-v1.0-el", "messages": [{"role": "user", "content": "Hello!"}], "max_tokens": 256}'

Python

import requests

r = requests.post(
    "https://api.poe.com/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
      "model": "fugu-ultra-v1.0-el",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ],
      "max_tokens": 256
    },
)
print(r.json())

JavaScript

const r = await fetch("https://api.poe.com/v1/chat/completions", {
  method: "POST",
  headers: {Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
  body: JSON.stringify({
    "model": "fugu-ultra-v1.0-el",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "max_tokens": 256
  }),
});
console.log(await r.json());

Request (JSON)

{
  "model": "fugu-ultra-v1.0-el",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 256
}

Response (JSON)

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "fugu-ultra-v1.0-el",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hi! How can I help?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

The address is taken from the provider's model list; check it against the provider's documentation.

Provider's API documentation

Source: AI Rate Card, https://airatecard.com/en/c/offer%3Apoe%7Cfugu-ultra-v1.0-el, prices checked 2026-11-04; seller's page: https://poe.com/fugu-ultra-v1.0-el

Technical details

ID: offer:poe|fugu-ultra-v1.0-el