Skip to main content
DeepL’s customization features let you control terminology, style, and consistency across your translations. They complement each other, and you can combine them in a single request:
FeatureWhat it controlsHow it’s applied
GlossariesExact translations for specific terms, like product names or industry vocabularyStored on your account; passed per request via glossary_id
Style rulesFormatting conventions (dates, numbers, punctuation) plus stored custom instructionsStored on your account; passed per request via style_id
Custom instructionsTone, phrasing, and domain-specific behavior via natural-language directivesInline per request via custom_instructions, or stored in a style rule list
Translation memoriesReuse of your previously approved translations for matching segmentsStored on your account; passed per request via translation_memory_id
All of these work with both text translation and document translation, and with all model_type values.
Glossaries and style rules are unique to each of DeepL’s global data centers and are not shared between them. Clients using regional endpoints can’t access glossaries or style rules created in the UI at this time.

​
Start here

Glossaries in the Real World

A hands-on tutorial: build a glossary and apply it to keep customer-facing terminology consistent.

Managing Glossaries

Create, edit, retrieve, and delete glossaries with the v3 endpoints, and use them in translations.

Using Style Rules

Build style rule lists with configured rules and custom instructions, and apply them via style_id.

Custom Instructions

Best practices for writing natural-language instructions that produce consistent results.

Using Translation Memories

Retrieve your translation memories and control the matching threshold in translation requests.

Customizations for Language Variants

Create customizations with root language codes and apply them to variants like pt-BR or fr-CA.

​
API reference

Glossaries, style rules, and translation memories each have management endpoints under the API Reference. If you’re still on the deprecated v2 glossary endpoints, see Glossary v2 vs v3 Endpoints for the differences and migration considerations.