What is Fugu used for?

Fugu is used for vision and multimodal work, reasoning, and agent workflows and tool use. The family description and listed model capabilities point to those workloads as the best fit.

How does Fugu compare to EvoLLM?

Fugu by Sakana AI is strongest where you need vision and multimodal work, while EvoLLM by Sakana AI is the closest related family to check for adjacent model selection. Fugu has 2 listed variants and reaches up to 1m context, while EvoLLM reaches up to 32k context, so compare the specs and pricing tables before choosing a production model.

Which Fugu model should I use?

For the lowest listed input price, start with Fugu Ultra through Sakana AI at $5/1M input tokens. For the most capable/latest local choice, evaluate Fugu with 1m context and reasoning, tool use, function calling, structured outputs, and multimodal inputs.

Fugu Models by Sakana AI

Sakana AIProprietary

2 models2026Up to 1m ctxFrom $5/1M input

Details

ResearcherSakana AI

LicenseProprietary

Commercial useCommercial use: conditional

Models2

Released2026

Max context1m

Capabilities

VisionAll models

MultimodalAll models

ReasoningAll models

Function CallingAll models

Tool UseAll models

Structured OutputsAll models

Links

Website

About

Fugu is Sakana AI's proprietary multi-agent orchestration system that behaves as a single API endpoint. It uses a trained coordinator/conductor model (based on TRINITY and Conductor architectures from ICLR 2026) to dynamically assign Thinker, Worker, and Verifier roles across a pool of frontier LLMs. Available via OpenAI-compatible API at api.sakana.ai. Not available in EU/EEA.

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view

FuguCurrent

Use when the workload needs 1m context, reasoning, and tool use.

2026-061m contextreasoningtool use

Fugu UltraCurrent

Use when the workload needs 1m context, reasoning, and tool use.

2026-061m contextreasoningtool use

Current Fugu variants with use-when guidance and lifecycle status
Model	Use when	Released	Signals	Status
Fugu	Use when the workload needs 1m context, reasoning, and tool use.	2026-06	1m contextreasoningtool use	Current
Fugu Ultra	Use when the workload needs 1m context, reasoning, and tool use.	2026-06	1m contextreasoningtool use	Current

Release Timeline

1 release group

2026-06

2 current

Fugu

1m contextreasoningtool use

Current

Fugu Ultra

1m contextreasoningtool use

Current

Specifications(2 models)

Fugu model specifications comparison
Model	Released	Context	Vision	Multimodal	Reasoning	Fn Calling	Tool Use	Structured Outputs
Fugu	2026-06	1m	Yes	Yes	Yes	Yes	Yes	Yes
Fugu Ultra	2026-06	1m	Yes	Yes	Yes	Yes	Yes	Yes

Available From(2 providers)

Sakana AI

Vercel AI Gateway

Pricing

Fugu model pricing by provider
Model	Provider	Input / 1M	Output / 1M	Type
Fugu Ultra	Sakana AI	$5	$30	Serverless
Fugu Ultra	Vercel AI Gateway	$5	$30	Serverless

Comparisons

All comparisons →

Frequently Asked Questions

What is Fugu used for?: Fugu is used for vision and multimodal work, reasoning, and agent workflows and tool use. The family description and listed model capabilities point to those workloads as the best fit.
How does Fugu compare to EvoLLM?: Fugu by Sakana AI is strongest where you need vision and multimodal work, while EvoLLM by Sakana AI is the closest related family to check for adjacent model selection. Fugu has 2 listed variants and reaches up to 1m context, while EvoLLM reaches up to 32k context, so compare the specs and pricing tables before choosing a production model.
Which Fugu model should I use?: For the lowest listed input price, start with Fugu Ultra through Sakana AI at $5/1M input tokens. For the most capable/latest local choice, evaluate Fugu with 1m context and reasoning, tool use, function calling, structured outputs, and multimodal inputs.

Models(2)