Sakanachat
Fugu Ultra
Fugu Ultra is the high-performance model in Sakana AI's Fugu family, built as a learned multi-agent orchestration system rather than a single monolithic model. It intelligently routes tasks across a pool of underlying models and can recursively invoke itself to solve complex problems more effectively. Optimized for multi-step reasoning, coding, and agentic workflows, Fugu Ultra supports configurable reasoning effort, native tool calling, and built-in web search. Its orchestration-based design makes it well suited for advanced autonomous agents and complex task execution requiring adaptive model coordination.
Pricing
Input$5.00 / 1M
Output$30.00 / 1M
Cache Write$0 / 1M
Cache Read$0 / 1M
Web Search$0 / 1M
Quick Start
Use the Apertis AI SDK, the OpenAI SDK, or make direct HTTP requests to our API.
Endpoint:
python
from openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.apertis.ai/v1") response = client.chat.completions.create( model="fugu-ultra", messages=[ {"role": "user", "content": "Hello!"} ], max_tokens=1024, temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(# model="fugu-ultra",# messages=[{"role": "user", "content": "Hello!"}],# extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )Supported Parameters
Common parameters: modelmessagesmax_tokenstemperaturetop_pstreamtools
Extended parameters: reasoning_effortstream_optionsthinkingextra_body
Cursor IDE Model IDs
Use these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.