North Mini Code

Name: North Mini Code
Author: Cohere

by CohereNorth

Open WeightModel weights are publicly available — can be downloaded and self-hostedAPIAvailable through a hosted API — pay per token, no self-hosting required

Released June 2026256K context≈ 192,000 words30B params

Compact yet powerful coding model using mixture-of-experts architecture. 30B total parameters but only 3B active at inference, enabling fast agentic software engineering.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Coding

Purpose-built for agentic coding

Moderate

Long Context

256K token context window

North Mini Code

by CohereNorth

Open WeightModel weights are publicly available — can be downloaded and self-hostedAPIAvailable through a hosted API — pay per token, no self-hosting required

Released June 2026256K context≈ 192,000 words30B params

Compact yet powerful coding model using mixture-of-experts architecture. 30B total parameters but only 3B active at inference, enabling fast agentic software engineering.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Coding

Purpose-built for agentic coding

Moderate

Long Context

256K token context window

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Glossary

AgenticA model designed to act autonomously by making decisions, selecting actions, and using tools to accomplish multi-step tasks.ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.InferenceThe process of running a trained model to generate predictions or outputs from new inputs.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.