Skip to content
AI Atlas
ModelAnnouncedOpen weightsfamily · North

North Small Translate

Cohere

quality58

Updated 3 h ago · first seen 11 Sept 2026

model_01M29DV4DKDBPPS82CHKF70QR4

Parameters
218B · 25B active
T2 · 3 h ago
Context
16K tokens
T2 · 3 h ago
Released
10 Sept 2026
T2 · 3 h ago
License
CC BY-NC 4.0
T2 · 3 h ago

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

17 claims · 17 properties

Familyfamily1

Claim history for Family
ValueValid from → toStatusSourceConfidenceExtractor
NorthcurrentcurrentCohere — docs & blogT2mediumllm

Versionversion1

Claim history for Version
ValueValid from → toStatusSourceConfidenceExtractor
1.0currentcurrentCohere — docs & blogT2mediumllm

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
10 Sept 2026currentcurrentCohere — docs & blogT2mediumllm

Statusstatus1

Claim history for Status
ValueValid from → toStatusSourceConfidenceExtractor
announcedcurrentcurrentCohere — docs & blogT2mediumllm

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weightscurrentcurrentCohere — docs & blogT2mediumllm

Licenselicense1

Claim history for License
ValueValid from → toStatusSourceConfidenceExtractor
CC BY-NC 4.0currentcurrentCohere — docs & blogT2mediumllm

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
MoEcurrentcurrentCohere — docs & blogT2mediumllm

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
218BcurrentcurrentCohere — docs & blogT2mediumllm

Active parametersactive_parameter_count1

Claim history for Active parameters
ValueValid from → toStatusSourceConfidenceExtractor
25BcurrentcurrentCohere — docs & blogT2mediumllm

Mixture of expertsis_moe1

Claim history for Mixture of experts
ValueValid from → toStatusSourceConfidenceExtractor
YescurrentcurrentCohere — docs & blogT2mediumllm

Context windowcontext_length1

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
16K tokenscurrentcurrentCohere — docs & blogT2mediumllm

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
16K tokenscurrentcurrentCohere — docs & blogT2mediumllm

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
TextcurrentcurrentCohere — docs & blogT2mediumllm

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
TextcurrentcurrentCohere — docs & blogT2mediumllm

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
TextcurrentcurrentCohere — docs & blogT2mediumllm

Languageslanguages1

Claim history for Languages
ValueValid from → toStatusSourceConfidenceExtractor
50+ languagescurrentcurrentCohere — docs & blogT2mediumllm

Hardware requirementshardware_requirements1

Claim history for Hardware requirements
ValueValid from → toStatusSourceConfidenceExtractor
1× B200 @ W4A4 or 2× H100s @ W4A4currentcurrentCohere — docs & blogT2mediumllm

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →