North Mini Code vs Step 5 Preview
Cohere · Canada | StepFun · China · 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 Step 5 Preview for sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents or 1m-token context window (64k max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available. Choose North Mini Code if you need self-hosting or data privacy; Step 5 Preview if you want a managed API.
North Mini Code (Cohere, Canada) and Step 5 Preview (StepFun, China) 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. Step 5 Preview is stepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. 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
- ▸Cost model: North Mini Code ships open weights you can self-host (hardware cost only, no per-token fee), while Step 5 Preview is API-metered at $1/$2.7 per 1M tokens. Your choice depends on whether you want zero marginal cost at the price of running infrastructure.
- ▸Context window: Step 5 Preview holds 3.9× more — 1M tokens (~1,500 pages) vs 256K (~384 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
- ▸Recency: Step 5 Preview is the newer model by about 3 months (released September 20, 2026), usually meaning fresher training data and capabilities.
- ▸Ecosystem: this is a Canada-vs-China matchup — they differ in pricing philosophy, data-residency options, and tooling ecosystems, not only benchmarks.
Side-by-side specs
| Spec | North Mini Code | Step 5 Preview |
|---|---|---|
| Provider | Cohere (Canada) | StepFun (China) |
| Released | June 9, 2026 | September 20, 2026 |
| Context window | 256K (~384 pages) | 1M tokens (~1,500 pages) |
| Price (in/out) | Open weight (self-host / free) | $1/$2.7 per 1M tokens |
| Open weight? | Yes — self-hostable | No — API only |
| Modalities | text, code | text, image, code |
| SWE-Bench Verified | 67.6% | Not published |
| MRCR v2 @ 1M | Not 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 its weights are open while Step 5 Preview is API-only.
Efficient sparse MoE — 3B active of 30B, runs on a single H100
North Mini Code
North Mini Code lists efficient sparse MoE — 3B active of 30B, runs on a single H100 among its strengths; Step 5 Preview does not.
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; Step 5 Preview does not.
Sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents
Step 5 Preview
Its 1M tokens window holds about 3.9× more than North Mini Code's 256K in a single prompt.
1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available
Step 5 Preview
North Mini Code is comparatively weak here — 256K context and modest general-intelligence index trail frontier models
67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%)
Step 5 Preview
StepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October — and it carries the larger 1M tokens context.
Lowest cost at scale
North Mini Code
Its weights are open, so at volume you pay for your own hardware instead of Step 5 Preview's $1/$2.7 per 1M tokens.
Largest single-prompt input
Step 5 Preview
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 Step 5 Preview, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ Step 5 Preview
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; Step 5 Preview is API-only.
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 sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents
→ Step 5 Preview
That is its strongest area.
An enterprise with regional data-residency rules
→ Step 5 Preview or North Mini Code
Origin (Canada vs China) 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.
Step 5 Preview: where it fits
StepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. Released September 20, 2026 by StepFun, it is built for sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents, 1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available, 67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%), and scores 44 on the Artificial Analysis Intelligence Index, ranking 27th of 653 models tracked.
Its trade-offs: trails closed frontier models on coding — 67.7% on DeepSWE v1.1 vs GPT-6 Astra's 74.1% and Claude Opus 5's 74.0%, open weights were promised for October 15, 2026 but hadn't shipped as of this writing — API-only for now despite the open-weight roadmap, a 'Preview' release, not StepFun's finished flagship — positioning and pricing may change once weights ship, and stepCodeBench and DeepSWE figures are StepFun's own reported numbers, not yet independently reproduced at scale. At $1 in / $2.7 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. North Mini Code gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Step 5 Preview 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 North Mini Code and Step 5 Preview 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 North Mini Code or Step 5 Preview better for coding?
Public SWE-Bench figures are not available for Step 5 Preview, 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 Step 5 Preview leans toward sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, North Mini Code or Step 5 Preview?
North Mini Code is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Step 5 Preview is API-metered at $1/$2.7 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?
Step 5 Preview — 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 North Mini Code and Step 5 Preview together?
Yes — a multi-model platform like LumiChats gives you North Mini Code, Step 5 Preview 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 Step 5 Preview?
Step 5 Preview — released September 20, 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.