For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
DASHBOARDPLAYGROUNDDOCSCOMMUNITYLOG IN
Guides and conceptsAPI ReferenceRelease NotesLLMUCookbooks
Guides and conceptsAPI ReferenceRelease NotesLLMUCookbooks
  • Get Started
    • Introduction
    • Installation
    • Creating a client
    • Playground
    • FAQs
  • Models
    • An Overview of Cohere's Models
      • Command A+
      • Command A
      • Command A Reasoning
      • Command A Translate
      • Command A Vision
      • Command R7B
      • Command R+
      • Command R
    • Embed
    • Rerank
    • Aya
  • Text Generation
    • Introduction to Text Generation at Cohere
    • Using the Chat API
    • Streaming Responses
    • Structured Outputs
    • Predictable Outputs
    • Advanced Generation Parameters
    • Retrieval Augmented Generation (RAG)
    • Tool Use
    • Tokens and Tokenizers
    • Migrating from the Generate API to the Chat API
    • Summarizing Text
    • Safety Modes
  • Embeddings (Vectors, Search, Retrieval)
    • Introduction to Embeddings at Cohere
    • Semantic Search with Embeddings
    • Multimodal Embeddings
    • Batch Embedding Jobs
  • Going to Production
    • API Keys and Rate Limits
    • Going Live
    • Deprecations
    • How Does Cohere's Pricing Work?
  • Integrations
    • Integrating Embedding Models with Other Tools
    • Cohere and LangChain
    • LlamaIndex and Cohere
  • Deployment Options
    • Overview
    • SDK Compatibility
  • Tutorials
    • Cookbooks
    • LLM University
    • Build Things with Cohere!
  • Responsible Use
    • Security
    • Usage Policy
    • Command A Technical Report
    • Command R and Command R+ Model Card
  • Cohere Labs
    • Cohere Labs Acceptable Use Policy
  • More Resources
    • Cohere Toolkit
    • Datasets
    • Improve Cohere Docs
LogoLogodocs
DASHBOARDPLAYGROUNDDOCSCOMMUNITYLOG IN
On this page
  • Description
  • What Can Command A Translate be Used For?
  • Getting Started
  • Conclusion
ModelsCommand

Cohere's Command A Translate Model

Was this page helpful?
Edit this page
Previous

Cohere's Command A Vision Model

Command A Vision model details and specifications
Next
Built with
Capabilities
MultilingualSafety ModesCitationsTool UseStructured OutputsReasoningImage Inputs
Pricing

For both trial keys and production keys, Command A Translate is free until rate limits are reached. Learn more about rate limits for different models and key types here.

To use Command A Translate in production, please reach out to sales at sales@cohere.com.

Specifications
    Context Window: 8,000 tokens
    Max Output Tokens: 8,000 tokens
    Knowledge Cutoff: June 1, 2024
API Endpoints
Model ID
command-a-translate-08-2025
Chat V2Chat V1Chat Completions
Try in Playground

Description

Automated translation from one language to another is one of the oldest applications of machine learning. Today’s LLMs have proven remarkably effective for these kinds of tasks, and Command A Translate is Cohere’s state of the art entry into the machine translation field. It delivers industry-leading performance on a variety of translation tasks across 23 languages, while offering enterprises full control of their data through private deployment options.

Command A Translate has a context length of 16K tokens (8K for input and 8K for output), 111B parameters, and can run on one or two GPUs (A100s / H100s).

What Can Command A Translate be Used For?

Command A Translate is excellent for translation tasks where you need answers that combine high quality and a low error rate. When utilized as part of our private deployment options, it is the best choice for enterprises wanting to translate data securely.

Supported Languages
  • English
  • French
  • Spanish
  • Italian
  • German
  • Portuguese
  • Japanese
  • Korean
  • Chinese
  • Arabic
  • Russian
  • Polish
  • Turkish
  • Vietnamese
  • Dutch
  • Czech
  • Indonesian
  • Ukrainian
  • Romanian
  • Greek
  • Hindi
  • Hebrew
  • Persian

Getting Started

You can perform translation of a text into another language with a simple prompt asking the model to translate a piece of text. In the sample below, we are doing this ‘programmatically’ by passing both the target language and content to translate as variables, but you can also just pass in a message saying "Please translate this into <target_language> for me."

PYTHON
1from cohere import ClientV2
2
3co = ClientV2(api_key="<YOUR API KEY>")
4
5target_language = "Spanish"
6content_to_translate = "Enterprises rely on translation for some of their most sensitive and business-critical documents and cannot risk data leakage, compliance violations, or misunderstandings. Mistranslated documents can reduce trust and have strategic implications."
7
8message = f"Translate everything that follows into {target_language}:\n\n{content_to_translate}"
9response = co.chat(
10 model="command-a-translate-08-2025",
11 messages=[{"role": "user", "content": message}],
12)
13print(response.message.content[0].text)

Here’s a sample output:

1Las empresas dependen de la traducción para algunos de sus documentos más sensibles y críticos para su negocio y no pueden permitirse el riesgo de fugas de datos, incumplimientos normativos o malentendidos. Los documentos mal traducidos pueden reducir la confianza y tener implicaciones estratégicas.

Conclusion

Command A Translate is great for one-shot translations but can also be embedded into more complicated workflows, such as translating long texts. Check out our cookbook for an example implementation.

Cohere enterprise clients may be interested in Deep Translation, our agentic approach to reaching the highest-quality translations. You can reach out to our sales team for more information.