North Small Translate, the Cohere model in numbers
North Small Translate in numbers: price per token, context window, independent benchmark scores and comparable models, based on public data checked on October 22, 2026.
Data as of October 22, 2026
Key figures
| Developer | Cohere |
|---|---|
| Released | September 9, 2026 |
| Context window | 32,768 tokens (≈ 49 pages) |
| Maximum output | 16,000 tokens |
| Input price | Not disclosed |
| Open weights | Yes |
| Reasoning mode | No |
| Tool calling | No |
| Structured output (JSON) | No |
| Accepted inputs | text |
| Providers offering it | 1 |
North Small Translate at a glance
Cohere released North Small Translate on September 9, 2026. It has no declared reasoning mode: it answers directly, without an extra billed thinking step. Its weights are published: you can download it and run it on your own servers, or use one of the 1 API providers that list it on models.dev. It is a very recent release.
We file it under open-weight models (68 models in this category on the site).
What do independent benchmarks say?
As of October 22, 2026, Epoch AI publishes no score for North Small Translate on our basket's benchmarks. To place it, rely on its specifications and price, then test it on your own cases.
What it can do
Its context window reaches 32,768 tokens, roughly 49 pages of text at 500 words per page: best kept for short exchanges and brief documents. A single answer can run to 16,000 tokens.
It accepts as input: text.
It is not listed as able to call tools, so it is a poor fit for driving an agent that has to act on other software.
What it costs
No public price is listed for North Small Translate on models.dev as of October 22, 2026. Check directly with Cohere.
What is it good for?
Given its category, North Small Translate is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.
Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.
Alternatives
In the same category, the models closest to North Small Translate are:
- Qwen3.6 35B-A3B (Alibaba Cloud (Qwen), index 55.3)
- Laguna XS 2.1 (Poolside, Poolside)
- Nemotron 3 Nano Omni 30B A3B Reasoning (NVIDIA, NVIDIA)
- GLM-5.3-Flash (Zhipu AI (Z.ai), index 71.9)
Similar models
- Qwen3.6 35B-A3B · Alibaba Cloud (Qwen) · index 55.3
- Laguna XS 2.1 · Poolside
- Nemotron 3 Nano Omni 30B A3B Reasoning · NVIDIA
- GLM-5.3-Flash · Zhipu AI (Z.ai) · index 71.9
Frequently asked questions
How much does North Small Translate cost?
No public price is listed on models.dev as of October 22, 2026.
What is the context window of North Small Translate?
32,768 tokens, roughly 49 pages of text. An answer can reach 16,000 tokens.
Is North Small Translate open source?
Its weights are published: you can install it on your own servers. Check the license before commercial use.
When was North Small Translate released?
North Small Translate was released on September 9, 2026, according to models.dev.
Can you build an agent with North Small Translate?
Not recommended: it is not listed as able to call tools.
Data sources
- Models.dev — Model data: models.dev (open-source project)
- OpenRouter — Market prices cross-checked with OpenRouter
Data as of October 22, 2026
Report an error
Does a figure, a date or a fact look wrong? Tell us: every report is checked.