> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Sakana AI

> 4 Sakana AI models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.

![Sakana AI](/_fern-img/45abdb7c98a9cc56e2ef187a82d5f8097429101e4bca969ec2946aae50939e69.webp)

## Sakana AI

## Models from Sakana AI

![Fugu Ultra v2.0](https://media.empiriolabs.ai/model-logos/fugu-ultra-v2-0.png)

[Fugu Ultra v2.0](/models/fugu-ultra-v2-0)

Flagship multi-agent conductor for the hardest reasoning, coding, and research work, with 1M context, image input, and web search.

![Fugu Ultra v1.1](https://media.empiriolabs.ai/model-logos/fugu-ultra-v1-1.png)

[Fugu Ultra v1.1](/models/fugu-ultra-v1-1)

Updated multi-agent conductor for hard reasoning, coding, and research, with distinct max effort, 1M context, image input, and web search.

![Fugu Ultra v1.0](https://media.empiriolabs.ai/model-logos/fugu-ultra-v1-0.png)

[Fugu Ultra v1.0](/models/fugu-ultra-v1-0)

Original multi-agent conductor for hard reasoning, coding, and research, with 1M context, image input, function calling, and web search.

![Fugu Max](https://media.empiriolabs.ai/model-logos/fugu-max.png)

[Fugu Max](/models/fugu-max)

Cost-efficient multi-agent conductor that assembles a right-sized expert team per task, with 1M context, image input, and web search.