Fugu Ultra

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.

sakana/fugu-ultra

Organization: Sakana AI
Family: fugu
Providers: 11
Context: 1,000,000
Output limit: —
Knowledge: —
Release: 2026-06-15
Updated: 2026-06-15
Weights: Closed
Input: text, image
Output: text
Capabilities: Tools, Reasoning, Structured

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

14 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
EmpirioLabs AI	fugu-ultra-v1-1	1,000,000	131,072	$5.00 / $30.00	Yes	Yes	Yes	View
EmpirioLabs AI	fugu-ultra-v1-0	1,000,000	131,072	$7.50 / $45.00	Yes	Yes	Yes	View
EmpirioLabs AI	fugu-ultra-v2-0	1,000,000	131,072	$5.00 / $30.00	Yes	Yes	Yes	View
Kilo Gateway	sakana/fugu-ultra	1,000,000	128,000	$5.00 / $30.00	Yes	Yes	Yes	View
LLM Gateway	sakana/fugu-ultra	1,000,000	1,000,000	$5.00 / $30.00	Yes	Yes	No	View
LLMTR	sakana/fugu-ultra	1,000,000	1,000,000	$5.00 / $30.00	Yes	Yes	Yes	View
Merge Gateway	sakana/fugu-ultra	1,000,000	128,000	$5.00 / $30.00	Yes	Yes	No	View
NanoGPT	sakana/fugu-ultra	1,000,000	16,384	$5.00 / $30.00	Yes	Yes	Yes	View
Sakana AIvia OpenRouter	sakana/fugu-ultra unknown	1,000,000	128,000	$5.00 / $30.00	Yes	Yes	Yes	View
Pioneer	sakana/fugu-ultra	1,000,000	131,072	$5.00 / $30.00	Yes	Yes	Yes	View
Requesty	fugu-ultra	1,048,576	131,072	$5.00 / $30.00	Yes	Yes	No	View
Sakana AI	fugu-ultra-20260615	1,000,000	1,000,000	$5.00 / $30.00	Yes	Yes	Yes	View
Sakana AI	fugu-ultra	1,000,000	1,000,000	$5.00 / $30.00	Yes	Yes	Yes	View
Vercel AI Gateway	sakana/fugu-ultra	1,000,000	1,000,000	$5.00 / $30.00	Yes	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$5.00Per 1M input tokens

Output from$30.00Per 1M output tokens

Available offers14Across 11 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 1 lowest-priced configuration

InputOutput

Sakana AIsakana

$5.00$30.00

sakana/fugu-ultraObserved Oct 4, 2026, 11:31 AM UTC

Input: $5.00
Output: $30.00
Cache read: $0.50

Additional fees and pricing conditions

web search: $0.01 / search

overrides · USD per token for token prices; time windows use UTC.

[
  {
    "prompt": "0.00001",
    "completion": "0.000045",
    "input_cache_read": "0.000001",
    "min_prompt_tokens": 272000
  }
]

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Sakana AIsakana	$5.00	$30.00	$0.50	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

Sakana AIsakana

7,288–7,596.7 ms

All latency percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Sakana AIsakana	7,288 ms	7,445.5 ms	7,540 ms	7,596.7 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

Sakana AIsakana

13.5–15.95 t/s

All throughput percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Sakana AIsakana	13.5 t/s	14.75 t/s	15.5 t/s	15.95 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 1 endpoint

Endpoint5 minutes30 minutes24 hours

Sakana AIsakanaObserved Oct 4, 2026, 11:31 AM UTC

—

100%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

gpqa diamondFugu Ultra

94.613%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	Fugu Ultrasakana/fugu-ultra	OpenRouter	94.613%	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

sakana/fugu-ultraObserved Oct 4, 2026, 11:31 AM UTC

Context: 1,000,000
Maximum output: 128,000
Tokenizer: Other
Input: text, image
Output: text
Moderation: No
Added to OpenRouter: 2026-06-24

Base URLhttps://openrouter.ai/api/v1

Model IDsakana/fugu-ultra

Version IDsakana/fugu-ultra-20260615

Reasoning

Required: Yes
Enabled by default: Yes
Default effort: xhigh
Supported efforts: max, xhigh, high

Supported parameters

include_reasoning
reasoning
reasoning_effort
structured_outputs
tool_choice
tools
web_search_options

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Fugu Ultra cost?

Listed rates start at $5.00 per million input tokens and $30.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Fugu Ultra?

There are 14 cataloged offers across 11 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,000,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Resources

Official model catalog ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 8d3e81ab99fd
Sep 12, 2026 · 6da80c9cfa0c