Skip to content

docs: remove latency_optimized restrictions and add release note#372

Open
jason-gardella-deepl wants to merge 3 commits into
mainfrom
fix/remove-latency-optimized-restrictions
Open

docs: remove latency_optimized restrictions and add release note#372
jason-gardella-deepl wants to merge 3 commits into
mainfrom
fix/remove-latency-optimized-restrictions

Conversation

@jason-gardella-deepl

Copy link
Copy Markdown
Member

Summary

Removes all documentation stating that model_type=latency_optimized is incompatible with certain features. latency_optimized is now fully supported with all Translate API
features.

Changes across 8 files

Restrictions removed:

  • Tag handling v2: Was "not compatible with latency_optimized" → now compatible
  • Style rules (style_id): Was "will be rejected" → now supported
  • Custom instructions: Was "will result in an error" → now supported
  • Translation memories: Was "will be rejected" → now supported
  • 81 new languages (Jan 2026): Was "not compatible with latency_optimized" → now compatible

Files changed:

  • api-reference/translate.mdx — Updated parameter descriptions for style_id, custom_instructions, translation_memory_id, and tag_handling_version
  • api-reference/style-rules.mdx — Updated style_id info box
  • api-reference/openapi.json — Updated schema descriptions
  • api-reference/openapi.yaml — Updated schema descriptions
  • docs/xml-and-html-handling/tag-handling-v2.mdx — Updated compatibility table and removed warning
  • docs/best-practices/custom-instructions.mdx — Removed error warning
  • docs/learning-how-tos/examples-and-guides/translation-beginners-guide.mdx — Updated special cases
  • docs/resources/roadmap-and-release-notes.mdx — Added June 15 release note + updated Jan 8 note

Release note added:

June 15 entry announcing latency_optimized is now supported for all features, listing the specific features that were previously restricted.

Context

This is the documentation counterpart to the Dynamic Workflows migration work. The DW workflow code now handles latency_optimized with all features via the
split_mode_follows_requested_model_type flag (dynamic-workflows!2111 and follow-ups).

🤖 Generated with Claude Code

jason-gardella-deepl and others added 2 commits June 15, 2026 09:03
latency_optimized is now fully compatible with all Translate API
features including tag handling v2, style rules, custom instructions,
translation memories, and all language pairs.

Removes outdated warnings, error descriptions, and compatibility
tables that stated these combinations would be rejected.

Adds a June 15 release note announcing the change.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@mintlify

mintlify Bot commented Jun 15, 2026

Copy link
Copy Markdown
Contributor

Preview deployment for your docs. Learn more about Mintlify Previews.

Project Status Preview Updated (UTC)
deepl-c950b784 🟢 Ready View Preview Jun 15, 2026, 1:13 PM

💡 Tip: Enable Workflows to automatically generate PRs for you.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
[Tag handling v2](/docs/xml-and-html-handling/tag-handling-v2) is compatible only with next-gen models and implicitly sets
`model_type` to `quality_optimized`. Setting both `model_type=latency_optimized` and `tag_handling_version=v2` will return an
error.
[Tag handling v2](/docs/xml-and-html-handling/tag-handling-v2) uses next-gen models and is compatible with all `model_type` values.

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe we could remove this box?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants