Skip to content

North Mini Code

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.

Providers
Capabilities
AIHubMix
aihubmix-byok
$0
$0
Unavailable
Cohere
cohere-byok
$0
$0
Unavailable
OpenRouter
openrouter-byok
$0
$0
Unavailable
OpenCode Zen
opencode-zen-byok
$0
$0
Unavailable
Usage analytics

Loading usage…

API & code
Uptime & Health
No uptime data yet

These providers haven't been health-probed for this model yet. The router still routes around upstreams that fail live requests — uptime fills in once probe history accrues.

Share cards
North Mini Code share card
North Mini Code
AIHubMix upstream share card
AIHubMix upstream
Cohere upstream share card
Cohere upstream
OpenRouter upstream share card
OpenRouter upstream
OpenCode Zen upstream share card
OpenCode Zen upstream
Credits
Use your own key

Run North Mini Code on your own key — your requests are billed by the provider. Pool callers pay AnyRouter credits.

No BYOK keys configured for this model yet.

Share a key with the pool to earn credits for every request it serves, covering your plan cost.

Text generation
Context length256,000 tokens
Max output204,800 tokens
Reasoning effortreasoning_effort
"high"

Default "high"

ArchitectureTransformer
Categorytext
ReleasedJun 18, 2026
Modalities
Capabilities