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...
- Modalities
- text → text
- In / out per 1M
- Free / Free
- Context
- 256K tokens
- Added
- Jun 17, 2026
- Max output
- 64K tokens
- Tokenizer
- Cohere
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | Free | — | Free |
| Output | Free | — | Free |
Providers
One company serves North Mini Code (free). Figures are each provider’s own list price per 1M tokens — your OpenKey price is in the card above.
| Provider | Context | Input /M | Output /M |
|---|---|---|---|
| Cohere | 256K | Free | Free |
Provider list from the OpenRouter catalog, Jul 28, 2026. All providers
Supported parameters
- frequency_penalty
- include_reasoning
- max_tokens
- presence_penalty
- reasoning
- seed
- stop
- temperature
- tool_choice
- tools
- top_k
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use
model cohere/north-mini-code:free.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"model": "cohere/north-mini-code:free",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="cohere/north-mini-code:free",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "cohere/north-mini-code:free",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);About North Mini Code (free)
North Mini Code is Cohere's first agentic coding model and the first release in its North family. It's a sparse mixture-of-experts design — 30B total parameters, 3B active per token — which keeps inference cheap while still routing through a larger parameter pool. Context window is 256,000 tokens, ahead of 52% of catalog models, and it supports tool calling plus optional reasoning you can toggle per request. Output modality is text only, capped at 64,000 completion tokens. Cohere is positioning this as the entry point for agentic code workflows rather than a general chat model.
It's free — both provider price and OpenKey price are $0.00 per 1M tokens for input and output, one of 25 free models on OpenKey out of 329 total. Against Cohere's own lineup it undercuts every priced sibling: Command R7B runs $0.0375/$0.15 per 1M, Command R (08-2024) runs $0.15/$0.60, and Command A and Command R+ both run $2.50/$10.00. Its 256K context beats Command's typical range and beats 52% of the full catalog. Reasoning is optional, not forced on every call.
Questions
- How much does North Mini Code (free) cost via API?
- It costs $0.00 per 1M input tokens and $0.00 per 1M output tokens — it's a free model. On OpenKey the 3% fee applies to provider price, so $0.00 x 1.03 is still $0.00. It's one of 25 free models available across OpenKey's 329-model catalog.
- What is North Mini Code's context window?
- North Mini Code supports a 256,000 token context window, which puts it ahead of 52% of models in the OpenKey catalog. That's enough room to hold large codebases or long multi-file diffs in a single request. Max completion length is capped separately at 64,000 tokens.
- Is North Mini Code free to use?
- Yes — both the provider price and the OpenKey price are $0.00 per 1M tokens for prompt and completion. It's flagged as a free model in the catalog, one of 25 free models OpenKey offers out of 329 total.
- Does North Mini Code support tool calling and reasoning?
- Yes, it supports tool calling (tools and tool_choice are in its supported parameters list) and optional reasoning you can enable per request via the reasoning and include_reasoning parameters. Reasoning isn't mandatory — it's off by default and toggled when needed. It does not support image or other non-text modalities; input and output are text only.
- How does North Mini Code compare to Cohere's Command models?
- North Mini Code is free, while every Command sibling carries a price: Command R7B costs $0.0375/$0.15 per 1M tokens, Command R (08-2024) costs $0.15/$0.60, and both Command A and Command R+ (08-2024) cost $2.50/$10.00 per 1M. North Mini Code also uses a sparse mixture-of-experts architecture (30B total, 3B active) rather than the dense design behind Command, and it's built specifically for agentic coding rather than general use.
More from Cohere
All Cohere models →
CohereCommand 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...
ctx 256K in $2.58 out $10.30
CohereCommand R7B (12-2024)
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...
ctx 128K in $0.039 out $0.154
CohereCommand R (08-2024)
command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...
ctx 128K in $0.154 out $0.618
CohereCommand R+ (08-2024)
command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...
ctx 128K in $2.58 out $10.30