Fugu Ultra v2.0 vs MiniMax M3.1 Flash
Sakana AI · Global | MiniMax · China · Updated June 2026
Quick verdict
Pick Fugu Ultra v2.0 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 or claims to outperform flagship models like gpt-6 astra and claude fable 5.1 despite its underlying orchestration pool reportedly excluding both of them. Pick MiniMax M3.1 Flash for $0.15/$0.60 per million tokens (cached $0.015) with flat pricing regardless of prompt length or 428b-parameter moe (about 23b active) with weights on hugging face from october 23, 2026. Choose MiniMax M3.1 Flash if you need self-hosting or data privacy; Fugu Ultra v2.0 if you want a managed API.
Fugu Ultra v2.0 (Sakana AI) and MiniMax M3.1 Flash (MiniMax) are two of the models people most often weigh against each other in 2026. 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. MiniMax M3.1 Flash is miniMax's October 19, 2026 always-thinking agentic Flash model - 1M context, text/image/video input, $0.15/$0.60 and open weights under a community license. They diverge most on price and open vs. closed weights — each quantified below from the models' real specs.
Key differences at a glance
- ▸Price: MiniMax M3.1 Flash is about 33× cheaper on input ($0.15/$0.6 per 1M tokens vs $5/$30 per 1M tokens) — a large enough gap that at scale it can be the single biggest line item in the decision.
- ▸Context window: both advertise 1M tokens (~1,500 pages). Tie on paper — test on your own long inputs, since usable recall varies by model.
- ▸Recency: MiniMax M3.1 Flash is the newer model by about 39 days (released October 19, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | Fugu Ultra v2.0 | MiniMax M3.1 Flash |
|---|---|---|
| Provider | Sakana AI (Global) | MiniMax (China) |
| Released | September 10, 2026 | October 19, 2026 |
| Context window | 1M tokens (~1,500 pages) | 1M tokens (~1,500 pages) |
| Price (in/out) | $5/$30 per 1M tokens | $0.15/$0.6 per 1M tokens |
| Open weight? | No — API only | Yes — self-hostable |
| Modalities | text | text, image, video, code |
| SWE-Bench Verified | Not published | Not published |
| MRCR v2 @ 1M | Not published | Not published |
Who wins what
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
MiniMax M3.1 Flash is comparatively weak here — benchmarks are mostly self-reported; no SWE-bench Verified figure published
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; MiniMax M3.1 Flash does not.
1M-token context window
Fugu Ultra v2.0
MiniMax M3.1 Flash is comparatively weak here — thinking is always on and default effort is max, which inflates output-token cost
$0.15/$0.60 per million tokens (cached $0.015) with flat pricing regardless of prompt length
MiniMax M3.1 Flash
Fugu Ultra v2.0 is comparatively weak here — pricing rises to roughly $10/$45 per million tokens for prompts above 272K tokens
428B-parameter MoE (about 23B active) with weights on Hugging Face from October 23, 2026
MiniMax M3.1 Flash
MiniMax's October 19, 2026 always-thinking agentic Flash model - 1M context, text/image/video input, $0.15/$0.60 and open weights under a community license — and it runs cheaper at $0.15/$0.6 per 1M tokens.
DeepSWE v1.1 of 73.7% and OSWorld V2 of 61.7 (MiniMax-reported)
MiniMax M3.1 Flash
Fugu Ultra v2.0 is comparatively weak here — 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
Lowest cost at scale
MiniMax M3.1 Flash
At $0.15/$0.6 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
→ MiniMax M3.1 Flash
At $0.15/$0.6 per 1M tokens it undercuts Fugu Ultra v2.0, and on millions of tokens that margin decides the monthly bill.
A team with data-privacy or self-hosting needs
→ MiniMax M3.1 Flash
Open weights let you run it on your own hardware; Fugu Ultra v2.0 is API-only.
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
It is specifically built for that.
Anyone whose priority is $0.15/$0.60 per million tokens (cached $0.015) with flat pricing regardless of prompt length
→ MiniMax M3.1 Flash
That is its strongest area.
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 are real: 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.
MiniMax M3.1 Flash: where it fits
MiniMax's October 19, 2026 always-thinking agentic Flash model - 1M context, text/image/video input, $0.15/$0.60 and open weights under a community license. Released October 19, 2026 by MiniMax, it is built for $0.15/$0.60 per million tokens (cached $0.015) with flat pricing regardless of prompt length, 428B-parameter MoE (about 23B active) with weights on Hugging Face from October 23, 2026, deepSWE v1.1 of 73.7% and OSWorld V2 of 61.7 (MiniMax-reported), and artificial Analysis Intelligence Index of 42, 13 points above MiniMax M3.
Its trade-offs: thinking is always on and default effort is max, which inflates output-token cost, behind DeepSeek V4.1 Flash 1017 on Artificial Analysis's independent index, custom MiniMax Community license: attribution required, and products above $20M annual revenue need written authorization, and benchmarks are mostly self-reported; no SWE-bench Verified figure published. At $0.15 in / $0.6 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
The defining split here is open vs. closed. MiniMax M3.1 Flash gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Fugu Ultra v2.0 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Want both Fugu Ultra v2.0 and MiniMax M3.1 Flash 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.
See pricingFrequently asked questions
Is Fugu Ultra v2.0 or MiniMax M3.1 Flash 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 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 while MiniMax M3.1 Flash leans toward $0.15/$0.60 per million tokens (cached $0.015) with flat pricing regardless of prompt length, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Ultra v2.0 or MiniMax M3.1 Flash?
MiniMax M3.1 Flash is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Fugu Ultra v2.0 is API-metered at $5/$30 per 1M tokens. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
Both advertise 1M tokens (~1,500 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both Fugu Ultra v2.0 and MiniMax M3.1 Flash together?
Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, MiniMax M3.1 Flash and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, Fugu Ultra v2.0 or MiniMax M3.1 Flash?
MiniMax M3.1 Flash — released October 19, 2026, about 39 days after Fugu Ultra v2.0.
Related comparisons
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.