---
title: "Sakana AI Integration"
source: https://docs.autohand.ai/integrations/sakana
---

# Sakana AI

Use Sakana AI's Fugu multi-agent orchestration models from Autohand through an OpenAI-compatible provider configuration.

## Overview

Sakana AI is available as the `sakana` provider. It is useful for teams that want a learned model orchestrator: Fugu routes, delegates, and synthesizes work across a pool of frontier models behind a single OpenAI-compatible endpoint.

Fugu is the balanced, low-latency variant for everyday coding and chat. Fugu Ultra coordinates a deeper agent pool for maximum answer quality on complex, multi-step engineering and research tasks.

## Setup

Create an API key from the [Sakana AI get-started console](https://console.sakana.ai/get-started), then confirm available model IDs in the [Sakana AI models console](https://console.sakana.ai/models).

``` bash
export SAKANA_API_KEY="your-sakana-api-key"

autohand --provider sakana --model fugu-ultra-20260615
```

## CLI configuration

``` json
{
  "provider": "sakana",
  "sakana": {
    "apiKey": "${SAKANA_API_KEY}",
    "baseUrl": "https://api.sakana.ai/v1",
    "model": "fugu-ultra-20260615"
  }
}
```

| Option | Description | Default |
|---|---|---|
| apiKey | Your Sakana AI API key | - |
| baseUrl | Sakana AI API endpoint | https://api.sakana.ai/v1 |
| model | Fugu model ID | fugu-ultra-20260615 |

## Models

Use `/model` to select a Fugu model or enter a custom model ID supported by your Sakana AI account. Check the [Sakana AI models console](https://console.sakana.ai/models) for the current catalog.

``` bash
/model sakana/fugu
/model sakana/fugu-ultra-20260615
```

| Model | Best for | Context |
|---|---|---|
| fugu | Balanced, low-latency coding and chat | 1M |
| fugu-ultra-20260615 | Maximum quality multi-agent orchestration | 1M |

## Notes

-   Fugu is not available in the EU/EEA at launch while Sakana AI works toward GDPR compliance.
-   By default, Sakana AI may use responses to improve its models. You can opt out from the Sakana AI console.
-   Fugu exposes orchestration token usage in `prompt_tokens_details` and `completion_tokens_details`, so you can see how many tokens the coordinator used behind the scenes.