Tasks and inputs
North Small Translate 1.0 is listed for Text generation. It accepts text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 13, 2026
North Small Translate 1.0 is Cohere’s specialist multilingual translation model, available through managed access and noncommercial weights.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
North Small Translate 1.0 is Cohere’s specialist multilingual translation model, available through managed access and noncommercial weights.
Cohere documents 218 billion total parameters, about 25 billion active parameters, a 16K context and 16K output allowance. The model covers more than fifty language and locale variants. Downloadable weights use CC BY-NC 4.0; commercial deployment terms and managed access should be checked separately with the publisher.
Include the document types your users actually submit: product descriptions, support messages, internal terminology and longer passages with formatting. Evaluate preservation of names, quantities, units, tone and paragraph structure. Include words whose meaning changes by domain and request the target locale explicitly. Have a fluent reviewer assess the output instead of treating a grammatically plausible translation as proof that meaning was preserved.
Use the north-small-translate-1-0 managed identifier when that route is enabled. Trial or production-key availability does not imply unlimited free production use; rate limits and commercial arrangements remain part of the access decision. For a local deployment, size hardware for the full sparse-expert checkpoint and keep the documented chat format.
For long documents, decide whether to translate them whole or segment them with shared terminology. Preserve context across segments and inspect consistency in repeated terms. Compare accepted translations and correction effort alongside latency, rather than ranking a translation model by a general chat benchmark.
Compare the model on the work you need to complete.
North Small Translate 1.0 is listed for Text generation. It accepts text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 16.38K context and 16.38K maximum output. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
The weights are downloadable under CC BY-NC 4.0. Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Anthropic
Claude’s small model for high-volume extraction, classification and routing, with adaptive thinking and a 1M-token context window.
Mistral AI
Mistral Large 4 is an open-weight multimodal model released in public preview on the publisher’s announced release, for general reasoning, coding and agent applications.
OpenAI
GPT-6.1 Sol is OpenAI's updated Sol model for coding and professional tasks. It accepts text and images and returns text.
inclusionAI
Ling 3.1 Flash is inclusionAI’s hybrid reasoning model for coding and tool agents, available through a hosted AI Gateway route.
Anthropic
Claude Sonnet 5.5 is an Anthropic language model that accepts text and images and returns text.
MiniMax
MiniMax M3.1 Flash Preview is a multimodal reasoning model for code and agent workflows, accessed through eligible MiniMax plans and tools.