Question 1

What is Fugu Max?

Accepted Answer

Fugu Max is a model from Sakana AI, released on Sep 11, 2026. 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...

Question 2

How much does Fugu Max cost?

Accepted Answer

On the Respan gateway, input starts at $2.00 per 1M tokens on every provider, and output starts at $6.00 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve Fugu Max on Respan?

Accepted Answer

2 providers serve Fugu Max: EmpirioLabs and OpenRouter.

Question 4

What is Fugu Max's context window?

Accepted Answer

Fugu Max accepts up to 1M tokens of context on its largest provider route.

Question 5

How do I use Fugu Max with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "fugu-max". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Fugu Max?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 26 tokens per second, and the lowest response latency was 2.6 seconds on OpenRouter. Speed varies with request size and provider.

Provider	Context	Input	Output	Capabilities
EmpirioLabs`empiriolabs/fugu-max`	1M	$2.00/M	$6.00/M
OpenRouter`openrouter/sakana/fugu-max`	1M	$2.00/M	$6.00/M

Fugu Max

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

Fugu Max FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.