Data as of November 13, 2026 · How the score is built
North Mini Code
Decision readingNorth Mini Code is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Email me when its price, rank or availability changes.
Is North Mini Code right for your job?
Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.
Where North Mini Code ranks by benchmark score:
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- north-mini-code-1-0Cohere North Mini Code model card
- Context window
- 256KCohere North Mini Code model card
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Cohere publishes the 30B-total, 3B-active MoE coding model under Apache 2.0 on Hugging Face (BF16 and FP8) and serves it as north-mini-code-1-0 through the Chat V2 API, Model Vault, OpenRouter, and OpenCode. The card documents a 256K input context and 64K maximum output.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordCohere North Mini Code model card
- Self-host
- North Mini Code needs ~24GB VRAM (1× NVIDIA RTX 4090 (24GB)).
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track North Mini Code, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
North Mini Code is a open weight model with a 256K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Cohere publishes the 30B-total, 3B-active MoE coding model under Apache 2.0 on Hugging Face (BF16 and FP8) and serves it as north-mini-code-1-0 through the Chat V2 API, Model Vault, OpenRouter, and OpenCode. The card documents a 256K input context and 64K maximum output.
Cohere’s June 9, 2026 launch post reports a 33.4 third-party coding-index score and presents SWE-Bench Verified, SWE-Bench Pro, Terminal Bench v2, and Terminal Bench Hard results as charts run through SWE-agent and ReAct harnesses without exact values in text; the Hugging Face post mixes pass@1 and pass@10 checkpoints. BenchLM therefore stores no provider rows and lets the external-signal refresh supply independent values. The row stays unranked.
The profile has no source-displayable benchmark row yet.
Last updated November 13, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Questions
How does North Mini Code perform overall in AI benchmarks?
North Mini Code does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Is North Mini Code open source?
North Mini Code is an open-weight model from Cohere. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does North Mini Code have full benchmark coverage on BenchLM?
No. North Mini Code currently has 12 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of North Mini Code?
North Mini Code has a documented context window of 256K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.