Back to models
Chat Models

Cohere

Command A Translate

Best Overall

Specialized text translation across 23 languages, with separate 8K input and 8K output limits.

Translation23 languages
Open AppBrowse All Models

At a glance

Know the model before you prompt.

Cohere API specifications
Context window
16K total · 8K input
Maximum output
8,000 tokens
Inputs → output
Text → Text
Knowledge cutoff
June 1, 2024

API model ID: command-a-translate-08-2025

Capabilities & boundaries

What it supports. Where the limits are.

Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.

Supported API features and tools

  • A translation-focused 111B-parameter model
  • Text translation across 23 supported languages
  • A documented 16K total envelope split into 8K input and 8K output
  • Translation workflows with explicit target-language and terminology instructions

Before you choose

  • This is a specialist text model, not a promise of vision, general tool use or Command A Reasoning's thinking controls.
  • The overview explains 16K total with 8K input and 8K output; its spec widget lists 8K context. Treat the input limit separately rather than assuming 16K can all be input.
  • Language expansion can increase output length. Split long texts at sensible boundaries and verify nothing was omitted.
  • Free API usage is limited by rate limits; production commercial terms require sales contact.
  • Context capacity is not a guarantee of complete recall. Keep source IDs, evaluate omissions and verify citations against the underlying documents.
  • A generated plan or tool call does not authorize or execute an external action. Use a configured integration, validate results and keep consequential changes behind human approval.

Reasoning behavior

The reviewed model-specific sources do not establish hybrid thinking controls or an effort-level list for this ID. Do not copy Command A Reasoning's thinking settings into other Command models. State the goal, evidence and answer format, then verify the result.

  • Use command-a-translate-08-2025 for the model covered here. The website slug is a navigation label, not necessarily the API model ID.
  • Specify the supported target language and retain names, units and product terminology. Keep instructions distinct from text to translate.
  • For long documents, segment by headings or paragraphs and retain a shared glossary across requests. Check continuity after recombining sections.
  • Use qualified human review for legal, medical, safety or other consequential translations; fluent language is not a guarantee of semantic accuracy.

Put it to work

Start with a more useful prompt.

Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.

Workflow 01

Localize product copy with a glossary

Preserve intent and brand terminology.

Translate the supplied product copy into the target language specified below. Follow the glossary exactly, preserve product names, numbers and units, and keep the same section structure. Flag ambiguous source phrases with a translator note rather than resolving them silently. Do not add claims, features or guarantees absent from the original.

Workflow 02

Review a translation for meaning drift

Look beyond fluency to factual consistency.

Compare this source text with its translation. Identify omissions, added promises, changed quantities and altered tone that affects meaning. Cite the source and translated passage for each issue. Suggest a corrected phrase and mark choices requiring a native speaker. Do not rewrite unrelated sentences just to change style.

Workflow 03

Plan a long-document translation

Preserve consistency within bounded requests.

Using this document outline and glossary, propose a segmentation plan for translation within the stated input and output budgets. Keep related clauses together, allow room for target-language expansion, and define checks for missing sections and terminology consistency. Return a plan only; do not claim the document has already been translated or reviewed.

Developer reference

Cohere API pricing

These are Cohere API reference terms, not EZ Ai Assist subscription prices.

View EZ Ai Assist plans

The current model card offers trial and production keys free usage until rate limits are reached. This is not unlimited free production. Cohere directs production deployments to its sales team. No public per-token production rate is established here.

  • Confirm limits for your exact model and key type; a production key alone is not evidence of unrestricted capacity.
  • Obtain deployment-specific commercial terms before budgeting. Do not substitute another Command model's token rates or show unverified prices as $0.

Common questions

A few things worth knowing.

How many languages are supported?

The model documentation lists 23. Use the provider's supported-language list and test the relevant language pair; do not interpret multilingual support as equal quality in every domain.

Is the context limit 8K or 16K?

The prose explains a 16K total envelope with 8K input and 8K output, while the widget lists 8K context. This guide shows the split explicitly so the total is not mistaken for the input allowance.

Can it serve as a general tool-using assistant?

This guide treats it as the documented translation specialist. It does not import tool, vision or reasoning controls from other Command A variants.

Is the translation service free at any volume?

No. The card's free usage is bounded by rate limits for both key types, and production users are directed to sales. Obtain deployment-specific terms before scaling.

Can it see current information automatically?

No. Model knowledge and a long context are not a live search service. Provide current evidence or connect an authorized retrieval workflow where supported, and verify the sources before acting on an answer.

How should I test it on my own work?

Use representative examples, explicit pass criteria and difficult counterexamples. Score factual support, omitted requirements and invalid outputs as well as latency and cost. Keep a human escalation path for uncertain or consequential results.

Are these API capabilities included in my EZ Ai Assist plan?

This guide describes the provider API, not subscription entitlements or a promise that every setting is exposed in the app. Check your workspace for model access and supported inputs, and use the EZ Ai Assist pricing page for plan details.

Check the source

Official documentation

Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.

Same provider

More from Cohere

Cohere

Command A+

Multimodal Cohere MoE with hybrid reasoning, 48-language support and a 128K context window.

Cohere

Command A

Text-focused Cohere model for grounded answers and tool workflows, with 256K context and 8K output.

Cohere

Command A Reasoning

Hybrid text reasoning with optional thinking budgets, 256K context and 32K output for evidence-heavy workflows.

Cohere

Command A Vision

Text and image understanding for documents, tables and charts, with up to 20 images per request and no tool use.