Both are Sakana AI models. Fugu Ultra v2.0 is the newer, generally stronger default; reach for Fugu Max when its lower price or a specific cost or latency profile matters more than the latest capabilities.
Fugu Max and Fugu Ultra v2.0 are both Sakana AI models, so the real question is not which lab to trust but which tier fits your workload and budget. Fugu Max is sakana AI's cost-first multi-agent orchestration model — not a single trained model, but a routed pool of models behind one API, priced at $2/$6 per million tokens. Fugu Ultra v2.0 is sakana AI's flagship multi-agent orchestration model, claiming best-or-joint-best results on 5 of 8 self-reported benchmarks against monolithic frontier models — $5/$30 per million tokens. Since both come from the same lab, the comparison below focuses on the tier-and-cost trade-offs that actually separate them.
Key differences
Price: Fugu Max is about 2.5× cheaper on input ($2/$6 per 1M tokens vs $5/$30 per 1M tokens) — meaningful once you are processing millions of tokens a month.
Context window: both advertise 1M tokens (~1,500 pages). Tie on paper — test on your own long inputs, since usable recall varies by model.
Specifications
Spec
Fugu Max
Fugu Ultra v2.0
Provider
Sakana AI (Global)
Sakana AI (Global)
Released
September 10, 2026
September 10, 2026
Context window
1M tokens (~1,500 pages)
1M tokens (~1,500 pages)
Price (in/out)
$2/$6 per 1M tokens
$5/$30 per 1M tokens
Open weight?
No — API only
No — API only
Modalities
text
text
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Cost-efficient multi-agent orchestration — undercuts Claude Sonnet 5 and Kimi K3 on output cost by a claimed 40-60%: Fugu Max — At $2/$6 per 1M tokens it undercuts Fugu Ultra v2.0 ($5/$30 per 1M tokens), and that gap compounds at volume.
1M-token context window at $2/$6 per million tokens: Fugu Max — Fugu Ultra v2.0 is comparatively weak here — pricing rises to roughly $10/$45 per million tokens for prompts above 272K tokens
OpenAI-compatible API — drop-in replacement for single-model integrations: Fugu Max — Fugu Ultra v2.0 is comparatively weak here — not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that dynamically routes tasks across a pool of other models, so head-to-head benchmark framing against monolithic frontier models should be read skeptically
Sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the DeepSWE coding-repair benchmark: Fugu Ultra v2.0 — Fugu Max is comparatively weak here — not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that routes tasks across a pool of other models, so raw benchmark comparisons to monolithic models can be misleading
Claims to outperform flagship models like GPT-6 Astra and Claude Fable 5.1 despite its underlying orchestration pool reportedly excluding both of them: Fugu Ultra v2.0 — Fugu Ultra v2.0 lists claims to outperform flagship models like GPT-6 Astra and Claude Fable 5.1 despite its underlying orchestration pool reportedly excluding both of them among its strengths; Fugu Max does not.
1M-token context window: Fugu Ultra v2.0 — Fugu Ultra v2.0 lists 1M-token context window among its strengths; Fugu Max does not.
Lowest cost at scale: Fugu Max — At $2/$6 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Which should you pick?
A cost-sensitive startup shipping high volume: Fugu Max — At $2/$6 per 1M tokens it undercuts Fugu Ultra v2.0, and on millions of tokens that margin decides the monthly bill.
Anyone whose priority is cost-efficient multi-agent orchestration — undercuts claude sonnet 5 and kimi k3 on output cost by a claimed 40-60%: Fugu Max — It is specifically built for that.
Anyone whose priority is sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the deepswe coding-repair benchmark: Fugu Ultra v2.0 — That is its strongest area.
Fugu Max: where it fits
Sakana AI's cost-first multi-agent orchestration model — not a single trained model, but a routed pool of models behind one API, priced at $2/$6 per million tokens. Released September 10, 2026 by Sakana AI, it is built for cost-efficient multi-agent orchestration — undercuts Claude Sonnet 5 and Kimi K3 on output cost by a claimed 40-60%, 1M-token context window at $2/$6 per million tokens, and openAI-compatible API — drop-in replacement for single-model integrations.
Its trade-offs are real: not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that routes tasks across a pool of other models, so raw benchmark comparisons to monolithic models can be misleading, the cheaper sibling to Fugu Ultra v2 — lower ceiling on the hardest reasoning tasks, and a young, first-generation product from Sakana AI's orchestration approach, unproven at scale versus established frontier labs. At $2 in / $6 out per million tokens, it sits in the mid price band.
Fugu Ultra v2.0: where it fits
Sakana AI's flagship multi-agent orchestration model, claiming best-or-joint-best results on 5 of 8 self-reported benchmarks against monolithic frontier models — $5/$30 per million tokens. Released September 10, 2026 by Sakana AI, it is built for sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the DeepSWE coding-repair benchmark, claims to outperform flagship models like GPT-6 Astra and Claude Fable 5.1 despite its underlying orchestration pool reportedly excluding both of them, and 1M-token context window.
Its trade-offs: not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that dynamically routes tasks across a pool of other models, so head-to-head benchmark framing against monolithic frontier models should be read skeptically, pricing rises to roughly $10/$45 per million tokens for prompts above 272K tokens, and benchmark comparisons against GPT-6 Astra and Claude Fable 5.1 are Sakana's own self-reported figures, not independently verified head-to-head scores. At $5 in / $30 out per million tokens, it sits in the premium price band.
The bottom line for this matchup
Because Fugu Max and Fugu Ultra v2.0 come from the same lab (Sakana AI), they share the same training philosophy and ecosystem — the decision is purely tier vs. cost. Fugu Ultra v2.0 is the more capable, more recent option; the other earns its place only when its price or latency profile fits a specific job better. Most teams should default to Fugu Ultra v2.0 and drop down only with a concrete reason.
Frequently asked questions
Is Fugu Max or Fugu Ultra v2.0 better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Fugu Max leans toward cost-efficient multi-agent orchestration — undercuts claude sonnet 5 and kimi k3 on output cost by a claimed 40-60% while Fugu Ultra v2.0 leans toward sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the deepswe coding-repair benchmark, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Max or Fugu Ultra v2.0?
Fugu Max is cheaper — $2/$6 per 1M tokens vs $5/$30 per 1M tokens, roughly 2.5× apart on input.
Which has the bigger context window?
Both advertise 1M tokens (~1,500 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Should I upgrade from Fugu Ultra v2.0 to Fugu Max?
Since both are Sakana AI models, the newer one (Fugu Ultra v2.0) is usually the better default unless you need a specific cost or latency profile from the other.
Which is newer, Fugu Max or Fugu Ultra v2.0?
They were released around the same time (September 10, 2026 and September 10, 2026).
Fugu Max vs Fugu Ultra v2.0
Sakana AI · Global | Sakana AI · Global · Updated June 2026
Quick verdict
Both are Sakana AI models. Fugu Ultra v2.0 is the newer, generally stronger default; reach for Fugu Max when its lower price or a specific cost or latency profile matters more than the latest capabilities.
Fugu Max and Fugu Ultra v2.0 are both Sakana AI models, so the real question is not which lab to trust but which tier fits your workload and budget. Fugu Max is sakana AI's cost-first multi-agent orchestration model — not a single trained model, but a routed pool of models behind one API, priced at $2/$6 per million tokens. Fugu Ultra v2.0 is sakana AI's flagship multi-agent orchestration model, claiming best-or-joint-best results on 5 of 8 self-reported benchmarks against monolithic frontier models — $5/$30 per million tokens. Since both come from the same lab, the comparison below focuses on the tier-and-cost trade-offs that actually separate them.
Key differences at a glance
▸Price: Fugu Max is about 2.5× cheaper on input ($2/$6 per 1M tokens vs $5/$30 per 1M tokens) — meaningful once you are processing millions of tokens a month.
▸Context window: both advertise 1M tokens (~1,500 pages). Tie on paper — test on your own long inputs, since usable recall varies by model.
Side-by-side specs
Spec
Fugu Max
Fugu Ultra v2.0
Provider
Sakana AI (Global)
Sakana AI (Global)
Released
September 10, 2026
September 10, 2026
Context window
1M tokens (~1,500 pages)
1M tokens (~1,500 pages)
Price (in/out)
$2/$6 per 1M tokens
$5/$30 per 1M tokens
Open weight?
No — API only
No — API only
Modalities
text
text
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Cost-efficient multi-agent orchestration — undercuts Claude Sonnet 5 and Kimi K3 on output cost by a claimed 40-60%
Fugu Max
At $2/$6 per 1M tokens it undercuts Fugu Ultra v2.0 ($5/$30 per 1M tokens), and that gap compounds at volume.
1M-token context window at $2/$6 per million tokens
Fugu Max
Fugu Ultra v2.0 is comparatively weak here — pricing rises to roughly $10/$45 per million tokens for prompts above 272K tokens
OpenAI-compatible API — drop-in replacement for single-model integrations
Fugu Max
Fugu Ultra v2.0 is comparatively weak here — not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that dynamically routes tasks across a pool of other models, so head-to-head benchmark framing against monolithic frontier models should be read skeptically
Sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the DeepSWE coding-repair benchmark
Fugu Ultra v2.0
Fugu Max is comparatively weak here — not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that routes tasks across a pool of other models, so raw benchmark comparisons to monolithic models can be misleading
Claims to outperform flagship models like GPT-6 Astra and Claude Fable 5.1 despite its underlying orchestration pool reportedly excluding both of them
Fugu Ultra v2.0
Fugu Ultra v2.0 lists claims to outperform flagship models like GPT-6 Astra and Claude Fable 5.1 despite its underlying orchestration pool reportedly excluding both of them among its strengths; Fugu Max does not.
1M-token context window
Fugu Ultra v2.0
Fugu Ultra v2.0 lists 1M-token context window among its strengths; Fugu Max does not.
Lowest cost at scale
Fugu Max
At $2/$6 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Fugu Max
At $2/$6 per 1M tokens it undercuts Fugu Ultra v2.0, and on millions of tokens that margin decides the monthly bill.
Anyone whose priority is cost-efficient multi-agent orchestration — undercuts claude sonnet 5 and kimi k3 on output cost by a claimed 40-60%
→ Fugu Max
It is specifically built for that.
Anyone whose priority is sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the deepswe coding-repair benchmark
→ Fugu Ultra v2.0
That is its strongest area.
Fugu Max: where it fits
Sakana AI's cost-first multi-agent orchestration model — not a single trained model, but a routed pool of models behind one API, priced at $2/$6 per million tokens. Released September 10, 2026 by Sakana AI, it is built for cost-efficient multi-agent orchestration — undercuts Claude Sonnet 5 and Kimi K3 on output cost by a claimed 40-60%, 1M-token context window at $2/$6 per million tokens, and openAI-compatible API — drop-in replacement for single-model integrations.
Its trade-offs are real: not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that routes tasks across a pool of other models, so raw benchmark comparisons to monolithic models can be misleading, the cheaper sibling to Fugu Ultra v2 — lower ceiling on the hardest reasoning tasks, and a young, first-generation product from Sakana AI's orchestration approach, unproven at scale versus established frontier labs. At $2 in / $6 out per million tokens, it sits in the mid price band.
Fugu Ultra v2.0: where it fits
Sakana AI's flagship multi-agent orchestration model, claiming best-or-joint-best results on 5 of 8 self-reported benchmarks against monolithic frontier models — $5/$30 per million tokens. Released September 10, 2026 by Sakana AI, it is built for sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the DeepSWE coding-repair benchmark, claims to outperform flagship models like GPT-6 Astra and Claude Fable 5.1 despite its underlying orchestration pool reportedly excluding both of them, and 1M-token context window.
Its trade-offs: not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that dynamically routes tasks across a pool of other models, so head-to-head benchmark framing against monolithic frontier models should be read skeptically, pricing rises to roughly $10/$45 per million tokens for prompts above 272K tokens, and benchmark comparisons against GPT-6 Astra and Claude Fable 5.1 are Sakana's own self-reported figures, not independently verified head-to-head scores. At $5 in / $30 out per million tokens, it sits in the premium price band.
The bottom line for this matchup
Because Fugu Max and Fugu Ultra v2.0 come from the same lab (Sakana AI), they share the same training philosophy and ecosystem — the decision is purely tier vs. cost. Fugu Ultra v2.0 is the more capable, more recent option; the other earns its place only when its price or latency profile fits a specific job better. Most teams should default to Fugu Ultra v2.0 and drop down only with a concrete reason.
Want both Fugu Max and Fugu Ultra v2.0 without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Fugu Max leans toward cost-efficient multi-agent orchestration — undercuts claude sonnet 5 and kimi k3 on output cost by a claimed 40-60% while Fugu Ultra v2.0 leans toward sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the deepswe coding-repair benchmark, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Max or Fugu Ultra v2.0?
Fugu Max is cheaper — $2/$6 per 1M tokens vs $5/$30 per 1M tokens, roughly 2.5× apart on input.
Which has the bigger context window?
Both advertise 1M tokens (~1,500 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Should I upgrade from Fugu Ultra v2.0 to Fugu Max?
Since both are Sakana AI models, the newer one (Fugu Ultra v2.0) is usually the better default unless you need a specific cost or latency profile from the other.
Which is newer, Fugu Max or Fugu Ultra v2.0?
They were released around the same time (September 10, 2026 and September 10, 2026).
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.