Sakana AI: Sakana Fugu Ultra v2NEW
sakana/fugu-ultra-v2Fugu 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 route tasks across a fixed pool of open and specialized models and to recursively call instances of itself. Fugu Ultra v2 prioritizes answer quality on complex multi-step reasoning, autonomous research, and full-stack software development, and does not rely on individual proprietary frontier models in its pool. It supports configurable reasoning effort (high, xhigh, max), function calling, structured outputs, image and PDF input, and built-in web search. Prompts above 272K tokens are billed at a higher rate. Orchestration tokens consumed by the system are billed as standard input/output tokens.
Additional rates
Above 272K prompt tokens the upstream charges more: 2× input, 1.5× output. Per-route rates are in the table below.
Parameters
messagesrequiredreasoning_efforthigh · xhigh · maxmax_tokensoptional · alias max_completion_tokensstreamtrue · falsetoolsfunction calling (OpenAI format)tool_choiceauto · none · requiredweb_search · · · providerrouting: order · only · ignore · sortstream_options{"include_usage": true}image_urlimage (data: URL)filePDF · DOCX · TXT · CSV · XLSX · PPTX (data: URL)How to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.chat.completions.create(
model="sakana/fugu-ultra-v2",
messages=[{"role": "user", "content": "Привет"}],
reasoning_effort="high", # high · xhigh · max
max_tokens=1024,
stream=False,
)
print(resp.choices[0].message.content)
# Стриминг: stream=True — ответ приходит чанками
for chunk in client.chat.completions.create(
model="sakana/fugu-ultra-v2",
messages=[{"role": "user", "content": "Привет"}],
stream=True,
):
print(chunk.choices[0].delta.content or "", end="", flush=True)
# с файлом (PDF · DOCX · TXT · CSV · XLSX · PPTX)
doc = client.chat.completions.create(
model="sakana/fugu-ultra-v2",
messages=[{"role": "user", "content": [
{"type": "text", "text": "Кратко перескажи документ"},
{"type": "file", "file": {
"filename": "doc.pdf",
"file_data": "data:application/pdf;base64,JVBERi0...",
}},
]}],
)
