Fugu Max vs North Mini Code

Sakana AI · Global  |  Cohere · Canada · Updated June 2026

Quick verdict

Pick Fugu Max for cost-efficient multi-agent orchestration — undercuts claude sonnet 5 and kimi k3 on output cost by a claimed 40-60% or 1m-token context window at $2/$6 per million tokens. Pick North Mini Code for agentic software engineering, code generation, and terminal tasks or efficient sparse moe — 3b active of 30b, runs on a single h100. Choose North Mini Code if you need self-hosting or data privacy; Fugu Max if you want a managed API.

Fugu Max (Sakana AI) and North Mini Code (Cohere) are two of the models people most often weigh against each other in 2026. 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. North Mini Code is cohere's first agentic coding model: an open-weight 30B/3B-active MoE built for real software-engineering and terminal tasks that runs on a single H100. They diverge most on price, context window and open vs. closed weights — each quantified below from the models' real specs.

Key differences at a glance

Side-by-side specs

SpecFugu MaxNorth Mini Code
ProviderSakana AI (Global) Cohere (Canada)
ReleasedSeptember 10, 2026 June 9, 2026
Context window1M tokens (~1,500 pages) 256K (~384 pages)
Price (in/out)$2/$6 per 1M tokens Open weight (self-host / free)
Open weight?No — API only Yes — self-hostable
Modalitiestext text, code
SWE-Bench VerifiedNot published 67.6%
MRCR v2 @ 1MNot 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

North Mini Code is comparatively weak here — text-only and coding-specialized — not multimodal or general-purpose

1M-token context window at $2/$6 per million tokens

Fugu Max

Its 1M tokens window holds about 3.9× more than North Mini Code's 256K in a single prompt.

OpenAI-compatible API — drop-in replacement for single-model integrations

Fugu Max

North Mini Code is comparatively weak here — 256K context and modest general-intelligence index trail frontier models

Agentic software engineering, code generation, and terminal tasks

North Mini Code

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

Efficient sparse MoE — 3B active of 30B, runs on a single H100

North Mini Code

Cohere's first agentic coding model: an open-weight 30B/3B-active MoE built for real software-engineering and terminal tasks that runs on a single H100 — and its weights are open while Fugu Max is API-only.

High throughput (up to 2.8x Devstral Small 2) at low latency

North Mini Code

North Mini Code lists high throughput (up to 2.8x Devstral Small 2) at low latency among its strengths; Fugu Max does not.

Lowest cost at scale

North Mini Code

Its weights are open, so at volume you pay for your own hardware instead of Fugu Max's $2/$6 per 1M tokens.

Largest single-prompt input

Fugu Max

Its 1M tokens window is about 3.9× larger than North Mini Code's 256K, fitting roughly 1,500 pages in one prompt.

Which should you pick?

A cost-sensitive startup shipping high volume

North Mini Code

At Open weight (self-host / free) it undercuts Fugu Max, and on millions of tokens that margin decides the monthly bill.

Someone analysing very long documents or codebases

Fugu Max

Larger 1M tokens window fits more in one prompt.

A team with data-privacy or self-hosting needs

North Mini Code

Open weights let you run it on your own hardware; Fugu Max is API-only.

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 agentic software engineering, code generation, and terminal tasks

North Mini Code

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.

North Mini Code: where it fits

Cohere's first agentic coding model: an open-weight 30B/3B-active MoE built for real software-engineering and terminal tasks that runs on a single H100. Released June 9, 2026 by Cohere, it is built for agentic software engineering, code generation, and terminal tasks, efficient sparse MoE — 3B active of 30B, runs on a single H100, high throughput (up to 2.8x Devstral Small 2) at low latency, and fully open weights under Apache 2.0 with fp8 and 4-bit builds.

Its trade-offs: text-only and coding-specialized — not multimodal or general-purpose, and 256K context and modest general-intelligence index trail frontier models. As an open-weight model, its running cost is your own hardware rather than a per-token fee.

The bottom line for this matchup

The defining split here is open vs. closed. North Mini Code gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Fugu Max 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 Max and North Mini Code 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 pricing

Frequently asked questions

Is Fugu Max or North Mini Code better for coding?

Public SWE-Bench figures are not available for Fugu Max, 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 North Mini Code leans toward agentic software engineering, code generation, and terminal tasks, and that positioning usually predicts which feels better on your codebase.

Which is cheaper, Fugu Max or North Mini Code?

North Mini Code is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Fugu Max is API-metered at $2/$6 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?

Fugu Max — 1M tokens vs 256K, about 3.9× larger. Useful only if the model actually reasons over the full window, which not all do.

Can I use both Fugu Max and North Mini Code together?

Yes — a multi-model platform like LumiChats gives you Fugu Max, North Mini Code 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 Max or North Mini Code?

Fugu Max — released September 10, 2026, about 3 months after North Mini Code.

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.