Is North Mini Code (free) free?

Yes. The pricing shown on this page for North Mini Code (free) is zero, so you are not charged for prompt or completion tokens. Free endpoints are rate limited — see the rate limit docs.

What is the context length of North Mini Code (free)?

North Mini Code (free) has a 256,000 token context window. It supports up to 64,000 completion tokens.

Does North Mini Code (free) support tool calling and structured outputs?

Yes. North Mini Code (free) accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.

Which providers serve North Mini Code (free)?

North Mini Code (free) is served by 1 provider on OpenRouter: Cohere.

What other text models does Cohere have?

Command A+, Command A, Command R7B (12-2024) and 2 more are other text models from Cohere.

When was North Mini Code (free) released?

North Mini Code (free) was released on June 17, 2026.

Cohere: North Mini Code (free)

cohere/north-mini-code:free

Model weights

Compare

North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize across agent harnesses such as OpenCode and SWE-Agent.

It offers a 256K-token context window with up to 64K tokens of output, supports interleaved reasoning and tool use via JSON schema, and is released open-weight under the Apache 2.0 license. Its small active-parameter footprint enables low-latency inference, including on local hardware.

Modalities

Price

Free

Context

256K

Released

Jun 17, 2026

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Latency / throughput


	Free	Free	0.48s	128 tok/s	100.00%

Input FreeOutput Free
128 tok/s100.00% uptime

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.80%

Availability over the last 3 days

Last 72 hours

Availability 99.80%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.81%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Cohere: North Mini Code (free) (Artificial Analysis)
Source	Benchmark	Score
Artificial Analysis	North Mini Code Intelligence Index	3.4
Artificial Analysis	North Mini Code Coding Index	36.5
Artificial Analysis	North Mini Code Agentic Index	1.1
Artificial Analysis	North Mini Code GPQA Diamond	75.7%
Artificial Analysis	North Mini Code HLE	11.1%
Artificial Analysis	North Mini Code IFBench	57.6%
Artificial Analysis	North Mini Code τ²-Bench Telecom	37.4%
Artificial Analysis	North Mini Code AA-LCR	37.3%
Artificial Analysis	North Mini Code τ-Bench Banking	6.4%
Artificial Analysis	North Mini Code GDPval-AA	0.0%
Artificial Analysis	North Mini Code CritPt	0.3%
Artificial Analysis	North Mini Code SciCode	38.8%
Artificial Analysis	North Mini Code Terminal-Bench Hard	31.1%
Artificial Analysis	North Mini Code Terminal-Bench 4.0	0.5%
Artificial Analysis	North Mini Code Terminal-Bench 2.1	35.6%
Artificial Analysis	North Mini Code AA-Omniscience Accuracy	18.4%
Artificial Analysis	North Mini Code AA-Omniscience Non-Hallucination Rate	16.5%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Kilo Code

Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.

250Btokens

Proto Agent

Proto is the personal agent for your business.

56.1Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

49.7Btokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

36.3Btokens

Cline

Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.

26.9Btokens

Rest of OpenRouter

3.56B

Top 5 Apps

2.51B

Not currently available through EU in-region routing. In-region routing docs

More models from Cohere

Embed 5 Fast

Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). It embeds text, images, and interleaved text and image content into a single vector space and is suited for high-volume query embedding, agent loops, and multilingual semantic search across 100+ languages.

It shares its embedding space with Embed 5 Pro, so documents indexed with Pro can be queried with Fast. Output dimensions are selectable from 256 to 2048, and input_type defaults to search_document when not set.

Embeddings$0.08/M tokens

Embed 5 Pro

Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). It embeds text, images, and interleaved text and image content into a single vector space and is suited for retrieval and RAG over long or domain-specific documents, visual and document search, and multilingual semantic search across 100+ languages.

It shares its embedding space with Embed 5 Fast, so a common pattern is to index a corpus with Pro and embed queries with Fast. Output dimensions are selectable from 256 to 2048, and input_type defaults to search_document when not set.

Embeddings$0.12/M tokens

Rerank 5 Fast

Rerank 5 Fast is the low-latency tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for high-throughput retrieval such as high-volume search, agent tool loops, and first-pass filtering before a more expensive step.

Relevance scores are calibrated to a 0-1 range so a fixed threshold behaves consistently across queries. Rerank 5 Pro is the higher-accuracy sibling for complex queries and long or domain-specific documents.

Rerank$0.02/M tokens

Rerank 5 Pro

Rerank 5 Pro is the higher-accuracy tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for retrieval pipelines where ranking quality matters most: complex or reasoning-heavy queries, long or domain-specific documents, and RAG systems that feed a small number of passages to a generator.

Relevance scores are calibrated to a 0-1 range so a fixed threshold behaves consistently across queries. Rerank 5 Fast is the lower-latency sibling for high-volume search and agent loops.

Rerank$0.05/M tokens

Command A+

Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured outputs (JSON object and JSON schema), optional reasoning, and configurable safety modes.

Text192K context$0.30 / $1.50

North Mini Code (free)

Text256K contextFree

Rerank 4 Pro

Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing required, and state of the art performance with low latency.

Rerank v3.5 is designed to reorder search results for improved relevance. It supports multi-aspect and semi-structured data reranking over 100+ languages. Ideal for refining results from semantic or keyword search pipelines.

Rerank$0.002/search

Command A

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.

Text256K context$2.50 / $10

Command R7B

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.