Sakana AI rolled out an orchestration layer that assembles and routes subtasks across a pool of models through one OpenAI-compatible endpoint, spotlighting the deeper Fugu Ultra variant for demanding engineering, scientific, and reasoning workloads while steering clear of export-controlled providers.
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
Developers can swap in the new service without changing their call patterns, though exact pricing and full general availability details beyond the current non-EU rollout remain unspecified.
Some researchers flag the announcement as potentially overstating originality, since the system leans on undisclosed mixes of closed frontier models rather than solely Sakana-trained components.
Many users praised Sakana's Fugu multi-agent orchestration system for its strong orchestration approach as a competitive moat, while others criticized restrictive usage limits and closed-source marketing.
No Digg Deeper questions have been answered for this story yet.
Mythos-class model available rn in Codex, thanks to @hardmaru & friends!
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
Human intelligence is fundamentally a collective intelligence. We solve complex problems by participating in a vast cultural network that builds upon ideas across generations.
I believe the strongest AI systems will become a collective intelligence, too.
Since we started Sakana AI, our core conviction has been that the most powerful AI systems will be collaborative ecosystems, not isolated monoliths. Evolution innovates under constraints, and the future belongs to systems that explicitly learn how to coordinate collective intelligence.
Today, we are taking a major step toward that future with the launch of Sakana Fugu.
Fugu dynamically orchestrates the world’s best models to tackle complex tasks. We are proving that a well-orchestrated pool of swappable agents can match restricted frontier models like Fable and Mythos.
But Fugu is about more than just performance. I believe that Orchestration Models are the next frontier, beyond bigger models.
Relying on a single company’s model for national infrastructure is a massive risk. As recent export controls have shown, access to top models can disappear overnight.
Collective intelligence is the practical hedge against this concentration of power. Fugu simply routes around vendor restrictions by relying on an entirely swappable agent pool.
I am incredibly proud of our Tokyo team for shipping this. By orchestrating the world’s models, we are delivering the resilient blueprint required for AI sovereignty.
Read our full vision and results here: https://sakana.ai/fugu-release 🐡
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
New Fable-equivalent from Sakana(!!!)
Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks.
Read the full blog: https://sakana.ai/fugu-release
Beyond Bigger Models: Why are Orchestration Models the Next Frontier
Progress in AI has been driven largely by giant, monolithic models. But the most powerful systems of the future will be collaborative ecosystems.
Today, this orchestration is no longer just a technical optimization. It has become a geopolitical and operational imperative.
For an organization or a nation, relying on a single company's model for critical infrastructure, finance, or governance is a material vulnerability. This risk is no longer a hypothetical possibility, but a reality.
As we have seen with recent export controls imposed on models like Fable and Mythos, access can disappear overnight.
Collective intelligence is the practical hedge against this concentration of power. Because Fugu orchestrates an underlying pool of swappable agents, it simply routes around vendor restrictions.
By orchestrating the world’s models, we are delivering the resilient blueprint required for true AI sovereignty.
Holy shit. 🤯
Huge drop from Sakana
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
“Without the risk of export controls” 🔥🔥
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
Another new idea to push the state of AI architectures forward. Sakana released a model that effectively uses a mixture of models to get work done. You get a single API but then the work gets farmed out the model that best performs the task.
“Fugu manages model selection, delegation, verification, and synthesis automatically. It solves tasks directly when that is enough, or coordinates a team of expert models when a problem calls for more. The complexity of a multi-agent system never reaches your code.”
This is generally how applied AI products are building their agent harnesses at this point, but the idea of making this an LLM that any developer can interact with is also a great idea. As we get more innovation with both frontier closed and OSS models, there’s going to be a ton of value produced for the layer that can route the best.
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
> without the risk of export controls
lol this is a closed source llm orchestrator that relies partly on closed source models api, they don't even report what percentage of closed vs open models the system uses to achieve these scores on benchmarks, this is very misleading
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
Once again busting the fable of Fable.
This company from Japan is getting near to run circles around Fable.
By the time they need the next marketing bump how will they tell us the sky is falling?
Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks.
Read the full blog: https://sakana.ai/fugu-release
Beyond Bigger Models: Why are Orchestration Models the Next Frontier
Progress in AI has been driven largely by giant, monolithic models. But the most powerful systems of the future will be collaborative ecosystems.
Today, this orchestration is no longer just a technical optimization. It has become a geopolitical and operational imperative.
For an organization or a nation, relying on a single company's model for critical infrastructure, finance, or governance is a material vulnerability. This risk is no longer a hypothetical possibility, but a reality.
As we have seen with recent export controls imposed on models like Fable and Mythos, access can disappear overnight.
Collective intelligence is the practical hedge against this concentration of power. Because Fugu orchestrates an underlying pool of swappable agents, it simply routes around vendor restrictions.
By orchestrating the world’s models, we are delivering the resilient blueprint required for true AI sovereignty.
A different kind of decentralization of intelligence!
Brilliant.
Human intelligence is fundamentally a collective intelligence. We solve complex problems by participating in a vast cultural network that builds upon ideas across generations.
I believe the strongest AI systems will become a collective intelligence, too.
Since we started Sakana AI, our core conviction has been that the most powerful AI systems will be collaborative ecosystems, not isolated monoliths. Evolution innovates under constraints, and the future belongs to systems that explicitly learn how to coordinate collective intelligence.
Today, we are taking a major step toward that future with the launch of Sakana Fugu.
Fugu dynamically orchestrates the world’s best models to tackle complex tasks. We are proving that a well-orchestrated pool of swappable agents can match restricted frontier models like Fable and Mythos.
But Fugu is about more than just performance. I believe that Orchestration Models are the next frontier, beyond bigger models.
Relying on a single company’s model for national infrastructure is a massive risk. As recent export controls have shown, access to top models can disappear overnight.
Collective intelligence is the practical hedge against this concentration of power. Fugu simply routes around vendor restrictions by relying on an entirely swappable agent pool.
I am incredibly proud of our Tokyo team for shipping this. By orchestrating the world’s models, we are delivering the resilient blueprint required for AI sovereignty.
Read our full vision and results here: https://sakana.ai/fugu-release 🐡
More than one way to get to to SOTA performance . Exciting.
Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks.
Read the full blog: https://sakana.ai/fugu-release
Beyond Bigger Models: Why are Orchestration Models the Next Frontier
Progress in AI has been driven largely by giant, monolithic models. But the most powerful systems of the future will be collaborative ecosystems.
Today, this orchestration is no longer just a technical optimization. It has become a geopolitical and operational imperative.
For an organization or a nation, relying on a single company's model for critical infrastructure, finance, or governance is a material vulnerability. This risk is no longer a hypothetical possibility, but a reality.
As we have seen with recent export controls imposed on models like Fable and Mythos, access can disappear overnight.
Collective intelligence is the practical hedge against this concentration of power. Because Fugu orchestrates an underlying pool of swappable agents, it simply routes around vendor restrictions.
By orchestrating the world’s models, we are delivering the resilient blueprint required for true AI sovereignty.
Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks.
Read the full blog: https://sakana.ai/fugu-release
Beyond Bigger Models: Why are Orchestration Models the Next Frontier
Progress in AI has been driven largely by giant, monolithic models. But the most powerful systems of the future will be collaborative ecosystems.
Today, this orchestration is no longer just a technical optimization. It has become a geopolitical and operational imperative.
For an organization or a nation, relying on a single company's model for critical infrastructure, finance, or governance is a material vulnerability. This risk is no longer a hypothetical possibility, but a reality.
As we have seen with recent export controls imposed on models like Fable and Mythos, access can disappear overnight.
Collective intelligence is the practical hedge against this concentration of power. Because Fugu orchestrates an underlying pool of swappable agents, it simply routes around vendor restrictions.
By orchestrating the world’s models, we are delivering the resilient blueprint required for true AI sovereignty.
"Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls."
me:
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
Sakana AI has unveiled Fugu Ultra, an orchestration layer that assembles and routes subtasks across a pool of models through one OpenAI-compatible endpoint.
On most benchmarks, it matches the performance of Fable and Mythos.
Fugu is a learned coordinator model inside a multi-agent system.
"Sakana Fugu is itself an LLM, trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the world's best models to tackle complex, multi-step tasks."
When you send a prompt, Fugu decides whether to answer alone or hand pieces of the job to other models, then it gathers the outputs and produces one final response.
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
i trust @hardmaru to cook
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://sakana.ai/fugu 🐡
Excited to try this one out!
Congrats to @hardmaru @YesThisIsLion & team!
Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks.
Read the full blog: https://sakana.ai/fugu-release
Beyond Bigger Models: Why are Orchestration Models the Next Frontier
Progress in AI has been driven largely by giant, monolithic models. But the most powerful systems of the future will be collaborative ecosystems.
Today, this orchestration is no longer just a technical optimization. It has become a geopolitical and operational imperative.
For an organization or a nation, relying on a single company's model for critical infrastructure, finance, or governance is a material vulnerability. This risk is no longer a hypothetical possibility, but a reality.
As we have seen with recent export controls imposed on models like Fable and Mythos, access can disappear overnight.
Collective intelligence is the practical hedge against this concentration of power. Because Fugu orchestrates an underlying pool of swappable agents, it simply routes around vendor restrictions.
By orchestrating the world’s models, we are delivering the resilient blueprint required for true AI sovereignty.
How does it work?
Sakana Fugu is itself an LLM, trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the world's best models to tackle complex, multi-step tasks.
As shown in this figure, Fugu is a multi-agent system that behaves like a single model. You send a request to one endpoint, and Fugu decides how to handle it internally.
Fugu manages model selection, delegation, verification, and synthesis automatically. It solves tasks directly when that is enough, or coordinates a team of expert models when a problem calls for more. The complexity of a multi-agent system never reaches your code.
At launch, Sakana Fugu comes in two models accessed via a single OpenAI-compatible API:
• Fugu balances strong performance with low latency for everyday work. It fits naturally into tools like Codex for coding, as well as chatbots and interactive services. You can also opt specific agents out of its pool for data compliance.
• Fugu Ultra is our flagship model tuned for maximum answer quality on hard, multi-step problems. It coordinates a deeper pool of expert agents for demanding work like AI research, cybersecurity analysis, and patent investigations.
time to cook.
Giving it a whirl! Excited.
New Fable-equivalent from Sakana(!!!)
oh and also the release blog is literally empty, no detail about cost, number of output token ect..
@SakanaAILabs could you give more details on the usage of the different models that this orchestrator uses? what percentage of each model is used for the different benchmarks?
also what is the cost per task and the number of output tokens for each benchmark?
@eliebakouch if any of the underlying models gets restricted they can just replace it with some other model and still call it fugu ultra, ez
> without the risk of export controls
lol this is a closed source llm orchestrator that relies partly on closed source models api, they don't even report what percentage of closed vs open models the system uses to achieve these scores on benchmarks, this is very misleading
@beffjezos Thanks, Beff!!
Mythos-class model available rn in Codex, thanks to @hardmaru & friends!
