Fugu Max
by Sakanasakana/fugu-max
LLMCompare cannot run Fugu Max 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 nowFugu Max 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
- Not published
Model facts synced from the OpenRouter model list on 21 Oct 2026.
Fugu Max pricing by route
A route is the service LLMCompare calls to reach the model. Fugu Max has 1 route. Prices are in US dollars.
| Route | On LLMCompare | Inputper 1M tokens | Outputper 1M tokens | Cache readper 1M tokens | Price verified on | Source |
|---|---|---|---|---|---|---|
| OpenRouterDefault | Not configured | $2.00 | $6.00 | $0.25 | openrouter.ai/sakana/fugu-max |
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 Max 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
- $0.005
- 6 credits
- Cost of 100 calls
- $0.50
- 600 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.
| Parameter | Type | Range or options | Default |
|---|---|---|---|
reasoning_effort | One of | maxxhighhigh | high |
About Fugu Max
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...
Description as published for this model. LLMCompare has not edited it.
Models to compare with Fugu Max
Text models from the same provider and models at the nearest price. The order is not a ranking.
| Add to comparison | Model | Context | Max output | Input priceper 1M tokens | Output priceper 1M tokens | Features | Released | On LLMCompare |
|---|---|---|---|---|---|---|---|---|
Sakana NamazuSakanasakana/sakana-namazu | 262k | 65.5k | $0.95 | $4.00 | ReasoningJSONToolsCacheVision | No route yet | ||
Fugu Ultra v2Sakanasakana/fugu-ultra-v2 | 1M | 128k | $5.00 | $30.00 | ReasoningJSONToolsCacheVision | No route yet | ||
Fugu UltraSakanasakana/fugu-ultra | 1M | 128k | $5.00 | $30.00 | ReasoningJSONToolsCacheVision | No route yet | ||
Grok 4.7SpaceXAIx-ai/grok-4.7 | 500k | 450k | $2.00 | $6.00 | ReasoningJSONToolsCacheVision | No route yet | ||
Qwen3.8 Max (0902)Qwenqwen/qwen3.8-max-0902 | 1M | 131k | $2.00 | $6.00 | ReasoningJSONToolsCacheVision | No route yet | ||
Qwen3.8 2.4T A95BQwenqwen/qwen3.8-2.4t-a95b | 1.05M | 909k | $2.00 | $6.00 | ReasoningJSONToolsCache | No route yet |
Questions about Fugu Max
- How much does Fugu Max cost?
- On the OpenRouter route, Fugu Max costs $2.00 per 1 million input tokens and $6.00 per 1 million output tokens, in US dollars. Input tokens that Fugu Max reads from the prompt cache cost $0.25 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
- What is the context length of Fugu Max?
- Fugu Max has a context length of 1,000,000 tokens and returns up to 128,000 output tokens in one call.
- What inputs does Fugu Max accept?
- Fugu Max accepts these inputs: Text, Image, File. Fugu Max returns: Text.
- Which reasoning effort levels does Fugu Max support?
- Fugu Max supports these reasoning effort levels: max, xhigh, high. Reasoning is always on for Fugu Max and cannot be turned off.
- Can I test Fugu Max on my own data?
- Not yet. LLMCompare lists the prices and parameters of Fugu Max, but no route to Fugu Max is configured on LLMCompare, so it cannot be selected for an evaluation.