north-mini-code-free · Cohere
Developed by Cohere, north-mini-code-free is the debut model of the North family and Cohere's first agentic coding model. This sparse mixture-of-experts model features 30B total parameters and 3B active parameters, designed and optimized for high performance. With an expansive context length of 256,000 tokens, it is well-suited for handling complex developer workflows and large codebases.
Developed by Cohere, north-mini-code-free is the debut model of the North family and Cohere's first agentic coding model. This sparse mixture-of-experts model features 30B total parameters and 3B active parameters, designed and optimized for high performance. With an expansive context length of 256,000 tokens, it is well-suited for handling complex developer workflows and large codebases.
North Mini Code (free) has a 256,000 token context window.
North Mini Code (free) accepts text input.
North Mini Code (free) supports reasoning, tool calling and long context. Per-protocol parameter support is listed in the capability table on this page.
North Mini Code (free) is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to north-mini-code-free — no other code changes needed.
North Mini Code (free) is developed by Cohere. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
North Mini Code (free) was released on June 9, 2026 by Cohere.
Cohere's stronger command model for multilingual agents and enterprise workflows
Rerank 4 is the most advanced set of reranker models available today, purpose-built to…
Rerank 4 is the most advanced set of reranker models available today, purpose-built to…
Cohere’s Embed 4 is a multilingual multimodal embedding model. It is capable of…
Command A is Cohere most performant model to date, excelling at tool use, agents…
Command A is Cohere most performant model to date, excelling at tool use, agents…
Use North Mini Code (free) via the AIHubMix unified API — one interface for every major LLM.