← All models

Sakana AI: Sakana Fugu MaxNEW
sakana/fugu-maxtextVisionFilesReasoning
Fugu Max is the cost-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-weights and specialized models, including NVIDIA's Nemotron family, and to recursively call instances of itself. Fugu Max dynamically selects efficient combinations of expert agents to improve quality and cost together, and is priced flat regardless of context length. It supports configurable reasoning effort (high, xhigh, max), function calling, structured outputs, image and PDF input, and built-in web search and web fetch. Orchestration tokens consumed by the system are billed as standard input/output tokens.
Price in / out
Cache, read / write
Context / Max output
1M / 128K
Released
Sep 11, 2026
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-max",
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-max",
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-max",
messages=[{"role": "user", "content": [
{"type": "text", "text": "Кратко перескажи документ"},
{"type": "file", "file": {
"filename": "doc.pdf",
"file_data": "data:application/pdf;base64,JVBERi0...",
}},
]}],
)
