Fugu Ultra v2

by Sakanasakana/fugu-ultra-v2

  • Text
  • No route yet
  • Released
  • Knowledge cutoff 28 August 2026

LLMCompare cannot run Fugu Ultra v2 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.

See the models that can be run now

Fugu Ultra v2 at a glance

Context length
1,000,000 tokens
Maximum output
128,000 tokens
Accepts
Text, Image, File
Returns
Text
Features
ReasoningJSON outputTool callingPrompt cachingImage input
Reasoning effort levels
maxxhighhighReasoning is always on for this model.
Released
11 Sep 2026
Knowledge cutoff
28 August 2026

Model facts synced from the OpenRouter model list on 21 Oct 2026.

Fugu Ultra v2 pricing by route

A route is the service LLMCompare calls to reach the model. Fugu Ultra v2 has 1 route. Prices are in US dollars.

Prices of Fugu Ultra v2 on each route
RouteOn LLMCompareInputper 1M tokensOutputper 1M tokensCache readper 1M tokensPrice verified onSource
OpenRouterDefaultNot configured$5.00$30.00$0.50openrouter.ai/sakana/fugu-ultra-v2

The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.

Cost calculator

Estimate what a batch of calls to Fugu Ultra v2 costs. The starting numbers are examples. Change them to match your task.

Part of the input tokens above, billed at the cache read price.

Billed in addition to the output tokens.

Cost per call
$0.02
24 credits
Cost of 100 calls
$2.00
2,400 credits

Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.

Parameters you can set

These are the parameters LLMCompare can set when it calls the model through OpenRouter.

Parameters of Fugu Ultra v2
ParameterTypeRange or optionsDefault
reasoning_effortOne ofmaxxhighhighxhigh

About Fugu Ultra v2

Fugu Ultra v2 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...

Description as published for this model. LLMCompare has not edited it.

Models to compare with Fugu Ultra v2

Text models from the same provider and models at the nearest price. The order is not a ranking.

Models to compare with Fugu Ultra v2
Add to comparisonModelContextMax outputInput priceper 1M tokensOutput priceper 1M tokensFeaturesReleasedOn LLMCompare
Fugu UltraSakanasakana/fugu-ultra1M128k$5.00$30.00ReasoningJSONToolsCacheVisionNo route yet
Fugu MaxSakanasakana/fugu-max1M128k$2.00$6.00ReasoningJSONToolsCacheVisionNo route yet
Sakana NamazuSakanasakana/sakana-namazu262k65.5k$0.95$4.00ReasoningJSONToolsCacheVisionNo route yet
GPT Chat LatestOpenAIopenai/gpt-chat-latest400k128k$5.00$30.00JSONToolsCacheVisionNo route yet
GPT-5.5OpenAIopenai/gpt-5.51.05M128k$5.00$30.00ReasoningJSONToolsCacheVisionNo route yet
GPT-4 TurboOpenAIopenai/gpt-4-turbo128k4.1k$10.00$30.00JSONToolsVisionNo route yet

Questions about Fugu Ultra v2

How much does Fugu Ultra v2 cost?
On the OpenRouter route, Fugu Ultra v2 costs $5.00 per 1 million input tokens and $30.00 per 1 million output tokens, in US dollars. Input tokens that Fugu Ultra v2 reads from the prompt cache cost $0.50 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
What is the context length of Fugu Ultra v2?
Fugu Ultra v2 has a context length of 1,000,000 tokens and returns up to 128,000 output tokens in one call.
What inputs does Fugu Ultra v2 accept?
Fugu Ultra v2 accepts these inputs: Text, Image, File. Fugu Ultra v2 returns: Text.
Which reasoning effort levels does Fugu Ultra v2 support?
Fugu Ultra v2 supports these reasoning effort levels: max, xhigh, high. Reasoning is always on for Fugu Ultra v2 and cannot be turned off.
Can I test Fugu Ultra v2 on my own data?
Not yet. LLMCompare lists the prices and parameters of Fugu Ultra v2, but no route to Fugu Ultra v2 is configured on LLMCompare, so it cannot be selected for an evaluation.