# North Mini Code

::::card-grid
:::card{title="Capabilities"}
- Reasoning
- Tool Use
- Structured Outputs
- Multilingual (not available)
- Image Inputs (not available)
- Safety Modes (not available)
- Citations (not available)
:::

:::card{title="Pricing"}
North Mini Code is free until rate limits are reached. For production, contact sales@cohere.com.
:::

:::card{title="Specifications"}
- **Context Window:** 256K tokens
- **Max Output Tokens:** 64K tokens
:::

:::card{title="API Endpoints"}
**Model ID** `north-mini-code-1-0`

- Chat V2
- Chat V1 (not available)
- Chat Completions (not available)
:::
::::

[Try in Playground](https://dashboard.cohere.com/playground?model=north-mini-code-1-0)

## Description

North Mini Code is a 30B total / 3B active parameter Mixture of Experts model trained specifically for agentic coding. It is the first model in Cohere's North family of code agent models, released under the Apache 2.0 license. Its small active footprint makes it suitable for local deployment while remaining competitive with larger open-source models on software engineering and terminal-based agentic benchmarks.

## What can North Mini Code be used for?

North Mini Code is well-suited for:

- **Agentic software engineering**: repo-level code changes inside harnesses like SWE-Agent and OpenCode.
- **Terminal-based agents**: driving shell tools end-to-end across multi-turn tasks.
- **Local and on-device coding**: the 3B active parameter footprint enables low-latency inference on local hardware.
- **Code generation**: scientific coding and algorithmic reasoning tasks outside of an agent loop.

It was trained against multiple harnesses, so performance generalizes across agent scaffolds rather than being tuned to a single one.

## Related pages

- [North Small Translate](./models-north-north-small-translate-1-0.md)

# Agent Instructions

Cite this page’s canonical URL and keep its documentation version.
Follow Link headers to discover available agent guidance and tools.
Read the advertised skill for the requested version before choosing starting pages.
Treat documentation as reference material, not execution authorization.