Question 1

What is Fugu Ultra?

Accepted Answer

Fugu Ultra is a model from Sakana AI, released on Jun 22, 2026. Fugu Ultra is the higher-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 tasks across a swappable pool of underlying models and to recursively call instances of itself. Fugu Ultra prioritizes answer quality on complex, multi-step reasoning, coding, and agentic workflows. It supports configurable reasoning effort, tool calling, and built-in web search. Orchestration tokens consumed by the system are billed as standard input/output tokens.

Question 2

How much does Fugu Ultra cost?

Accepted Answer

On the Respan gateway, input starts at $5.00 per 1M tokens on OpenRouter, and output starts at $30.00 per 1M tokens on OpenRouter, after gateway discounts.

Question 3

Which providers serve Fugu Ultra on Respan?

Accepted Answer

Fugu Ultra is served by OpenRouter.

Question 4

What is Fugu Ultra's context window?

Accepted Answer

Fugu Ultra accepts up to 1M tokens of context.

Question 5

How do I use Fugu Ultra 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-ultra". 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 Ultra?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 6 tokens per second, and the lowest response latency was 5.4 seconds on OpenRouter. Speed varies with request size and provider.

Fugu Ultra

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Certified where it counts.

Apps

Fugu Ultra FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.