North Mini Code vs Reka Flash 3.1

Cohere · Canada  |  Reka AI · US · Updated June 2026

Quick verdict

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. Pick Reka Flash 3.1 for a 21b-parameter reasoning model, small enough for local/on-device deployment (a 3.5-bit quantized build exists) or strong base for fine-tuning agentic tasks - notably improved coding since the original flash 3.

North Mini Code (Cohere, Canada) and Reka Flash 3.1 (Reka AI, US) line up two different AI ecosystems against each other — a comparison that is as much about cost philosophy and openness as raw capability. 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. Reka Flash 3.1 is reka AI's compact 21B open-weight reasoning model - small enough to run locally, from a team of DeepMind and Meta alumni. Their biggest split is context window, and the breakdown below shows exactly how that plays out for your workload.

Key differences at a glance

Side-by-side specs

SpecNorth Mini CodeReka Flash 3.1
ProviderCohere (Canada) Reka AI (US)
ReleasedJune 9, 2026 July 2025
Context window256K (~384 pages) 32K (~49 pages)
Price (in/out)Open weight (self-host / free) Open weight (self-host / free)
Open weight?Yes — self-hostable Yes — self-hostable
Modalitiestext, code text, code
SWE-Bench Verified67.6% Not published
MRCR v2 @ 1MNot published Not published

Who wins what

Agentic software engineering, code generation, and terminal tasks

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 it carries the larger 256K context.

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 it is the newer of the two.

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

North Mini Code

Reka Flash 3.1 is comparatively weak here — a relatively small 32K context window next to million-token frontier models

A 21B-parameter reasoning model, small enough for local/on-device deployment (a 3.5-bit quantized build exists)

Reka Flash 3.1

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

Strong base for fine-tuning agentic tasks - notably improved coding since the original Flash 3

Reka Flash 3.1

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

Fully open weights (Apache 2.0) from a frontier-caliber research team

Reka Flash 3.1

Reka Flash 3.1 lists fully open weights (Apache 2.0) from a frontier-caliber research team among its strengths; North Mini Code does not.

Largest single-prompt input

North Mini Code

Its 256K window is about 7.8× larger than Reka Flash 3.1's 32K, fitting roughly 384 pages in one prompt.

Which should you pick?

Someone analysing very long documents or codebases

North Mini Code

Larger 256K window fits more in one prompt.

Anyone whose priority is agentic software engineering, code generation, and terminal tasks

North Mini Code

It is specifically built for that.

Anyone whose priority is a 21b-parameter reasoning model, small enough for local/on-device deployment (a 3.5-bit quantized build exists)

Reka Flash 3.1

That is its strongest area.

An enterprise with regional data-residency rules

Reka Flash 3.1 or North Mini Code

Origin (Canada vs US) affects where data is processed and which compliance regime applies — check the provider's terms for your region.

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 are real: 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.

Reka Flash 3.1: where it fits

Reka AI's compact 21B open-weight reasoning model - small enough to run locally, from a team of DeepMind and Meta alumni. Released July 2025 by Reka AI, it is built for a 21B-parameter reasoning model, small enough for local/on-device deployment (a 3.5-bit quantized build exists), strong base for fine-tuning agentic tasks - notably improved coding since the original Flash 3, fully open weights (Apache 2.0) from a frontier-caliber research team, and built by alumni from Google DeepMind and Meta's AI labs.

Its trade-offs: a relatively small 32K context window next to million-token frontier models, smaller and less capable overall than flagship frontier models from major labs, and reka's broader roadmap has shifted toward robotics/world models after merging with Moonvalley in June 2026, raising questions about ongoing LLM investment. As an open-weight model, its running cost is your own hardware rather than a per-token fee.

The bottom line for this matchup

This is less "which is smarter" and more "which ecosystem fits." North Mini Code (Canada) and Reka Flash 3.1 (US) differ on pricing philosophy, data-residency, and tooling as much as on raw scores. The pragmatic move is to run one real task through both and judge the outputs against your own constraints — including where your data is allowed to be processed.

Want both North Mini Code and Reka Flash 3.1 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 North Mini Code or Reka Flash 3.1 better for coding?

Public SWE-Bench figures are not available for Reka Flash 3.1, so the honest test is your own repository — run an identical real bug through both. By design, North Mini Code leans toward agentic software engineering, code generation, and terminal tasks while Reka Flash 3.1 leans toward a 21b-parameter reasoning model, small enough for local/on-device deployment (a 3.5-bit quantized build exists), and that positioning usually predicts which feels better on your codebase.

Which is cheaper, North Mini Code or Reka Flash 3.1?

They are priced almost identically, so cost will not decide between them.

Which has the bigger context window?

North Mini Code — 256K vs 32K, about 7.8× larger. Useful only if the model actually reasons over the full window, which not all do.

Can I use both North Mini Code and Reka Flash 3.1 together?

Yes — a multi-model platform like LumiChats gives you North Mini Code, Reka Flash 3.1 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, North Mini Code or Reka Flash 3.1?

North Mini Code — released June 9, 2026, about 11 months after Reka Flash 3.1.

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.