> ## Documentation Index
> Fetch the complete documentation index at: https://api-docs.ollang.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Translation and LLM Providers
> Every translation engine selectable in Ollang Workflows — Ollang Agentic, OpenAI, Claude, Gemini, DeepL, Amazon, Cohere, Mistral, Qwen, and Llama — with capability notes and order-type support.
Translation runs in the `translate` step and serves three very different jobs: **document** localization, **subtitle** translation against timed dialogue, and **dubbing script** generation where the output has to fit a timing budget and sound speakable.
The catalog spans purpose-built machine translation (DeepL, Amazon), frontier general-purpose LLMs (OpenAI, Claude, Gemini), efficient open-weight models (Llama, Qwen, Mistral), and Ollang's own agentic localization workflow. They are not interchangeable — they differ in language coverage, context window, steerability, and which Order Types they serve.
## Choosing by job
| If your priority is… | Start with |
| ----------------------------------------------- | -------------------------------------------------------------------------------------------- |
| Maximum localization quality, culturally aware | [Agentic Localization](#ollang-agentic) |
| High-volume documents with fast turnaround | [DeepL](#deepl) or [Agentic Turbo](#ollang-agentic) |
| Frontier capability on quality-critical content | [GPT-5.6-Sol](#openai), [Claude 5 Opus](#anthropic-claude), [Gemini 3.1 Pro](#google-gemini) |
| The hardest source material | [Claude 5 Fable](#anthropic-claude) |
| Fast, efficient throughput at scale | [GPT-5.6-Luna](#openai), [Gemini 3.7 Flash](#google-gemini) |
| Strict terminology under enterprise controls | [Cohere Command A](#cohere), [Amazon](#amazon-translate) |
| Documents with diagrams, screenshots, or scans | [Gemini](#google-gemini), [DeepL Extended](#deepl) |
| Chinese–English and long-tail languages | [Qwen3](#qwen) |
| Long-form consistency across a document set | [Claude](#anthropic-claude) |
| Subtitle output constrained to a length budget | [Amazon](#amazon-translate) |
Language coverage across this catalog ranges from 12 to over 240. Check the family's coverage before committing a Workflow — it is the most common reason one has to be reconfigured.
***
## Ollang Agentic
Ollang's own localization workflow, and the only provider in this catalog that is a *pipeline* rather than a single model. It selects and combines agents per segment based on content type, domain, and structural complexity, then reconciles their output.
| Model | Provider tag | Order types | Status |
| -------------------- | ------------------- | ------------------------------ | ------------ |
| Agentic Localization | `ollangAITranslate` | Document, Subtitle, AI Dubbing | **Default** |
| Agentic Turbo | `agentic-turbo` | Document, Subtitle, AI Dubbing | Experimental |
**Agentic Localization** covers end-to-end localization of text, documents, subtitles, and dubbing scripts across 100+ languages. It is the default because localization quality — not translation accuracy alone — is what most Orders are judged on.
**Agentic Turbo** is the same shape of workflow tuned for throughput, aimed at high-volume pipelines that still need contextual quality rather than raw machine translation.
Agentic Turbo is experimental. Benchmark it against your existing provider in a separate Folder before moving a production Global Workflow onto it.
***
## OpenAI
The widest model ladder in the catalog. The current generation is **GPT-5.6**, which ships as Luna, Terra, and Sol in ascending capability. All three carry a **1.05M-token context window and 128K max output** — the tiers differ in capability, not in how much text they can hold. Ollang exposes the two ends of that range.
| Model | Provider tag | Context | Status |
| ------------ | --------------------- | ------- | --------- |
| GPT-5.6-Sol | `openai/gpt-5.6-sol` | 1.05M | **New** |
| GPT-5.6-Luna | `openai/gpt-5.6-luna` | 1.05M | **New** |
| GPT-5.4 | `openai/gpt-5.4` | \~1M | **New** |
| GPT-5.2 | `openai/gpt-5.2` | 400K | Available |
| GPT-5 | `openai/gpt-5` | — | Available |
| GPT-4.1 | `openai` | 1M | Available |
| o4-mini | `openai/o4-mini` | — | Available |
All OpenAI models serve Document, Subtitle, and AI Dubbing Orders.
**GPT-5.6-Sol** is OpenAI's most capable model, for complex translation and localization where nuance, terminology accuracy, consistency, and reliable instruction-following all have to hold at once. It supersedes the earlier 5.x tiers on capability.
**GPT-5.6-Luna** is the efficiency tier of the same generation, built for everyday translation at volume with minimal latency — while carrying the same 1.05M context window as Sol. That combination is unusual: whole-document context on a throughput-oriented tier.
**GPT-5.4**, **GPT-5.2**, **GPT-5**, **GPT-4.1**, and **o4-mini** are earlier tiers, retained for Workflows already benchmarked against them. GPT-5.4 brought roughly 1M-token context and configurable reasoning effort; GPT-4.1 remains a sensible mid-tier workhorse; o4-mini is the compact reasoning option with an efficient tokenizer for non-English text.
Luna and Sol share a context window and a generation. A Global Workflow on Luna with Sol overridden at Folder level for customer-facing content is the configuration that gets the most out of this family.
***
## Anthropic Claude
Consistently the strongest family for long-form coherence, register control, and terminology consistency across a document — the qualities that show up in human review rather than in automatic scores.
The current lineup all carry a **1M-token context window with 128K max output** and adaptive thinking. On Anthropic's current tokenizer, 1M tokens is roughly 555,000 words.
| Model | Provider tag | Anthropic positioning | Status |
| ----------------- | ----------------------------- | ---------------------------------------------------------------------------------- | --------- |
| Claude 5 Fable | `anthropic/claude-fable-5` | Highest available capability; next-generation intelligence for long-running agents | **New** |
| Claude 5 Opus | `anthropic/claude-opus-5` | Complex agentic and enterprise work | **New** |
| Claude 5 Sonnet | `anthropic/claude-sonnet-5` | Best combination of speed and intelligence | **New** |
| Claude 4.7 Opus | `anthropic/claude-opus-4.7` | Legacy | Available |
| Claude 4.5 Opus | `anthropic/claude-opus-4.5` | Legacy | Available |
| Claude 4.5 Sonnet | `anthropic/claude-4.5-sonnet` | Legacy | Available |
| Claude 4 Sonnet | `claude` | Superseded | Available |
All Claude models serve Document, Subtitle, and AI Dubbing Orders, and all support text and image input.
**Claude 5 Fable** is Anthropic's highest-capability model. Its thinking is adaptive and always on, and its comparative latency is the slowest in the lineup. Reserve it for genuinely hard content — dense technical or legal source, structurally ambiguous material, or work where a second human pass would otherwise be needed.
**Claude 5 Opus** offers the same 1M context and 128K output with the most recent knowledge cutoff in the family, and is the sensible default within Claude for quality-critical localization.
**Claude 5 Sonnet** is positioned by Anthropic as the best combination of speed and intelligence. If a Workflow currently runs Claude 4 or 4.5 Sonnet, this is a straight upgrade.
The **4.x tiers** remain available for existing benchmarks, each now matched or beaten by its Claude 5 equivalent.
***
## Google Gemini
The most natively multimodal family in the catalog — text, images, audio, video, and PDF as first-class inputs — with million-token context windows across the current generation.
| Model | Provider tag | Status at Google | Ollang status |
| ---------------------- | ------------------------------- | ---------------- | ------------- |
| Gemini 3.1 Pro Preview | `google/gemini-3.1-pro-preview` | Preview | **New** |
| Gemini 3.7 Flash | `google/gemini-3.7-flash` | Stable | **New** |
| Gemini 3 Pro Preview | `google/gemini-3-pro-preview` | Superseded | Available |
| Gemini 2.5 Pro | `gemini` | Stable | Available |
All Gemini models serve Document, Subtitle, and AI Dubbing Orders.
**Gemini 3.7 Flash** is now a **stable** release rather than a preview. It carries a 1M-token context window with 64K output, accepts text, images, audio, and video, and has a knowledge cutoff of March 2026 — the most recent of any model in this catalog. It is the default recommendation within Gemini for most localization work.
**Gemini 3.1 Pro Preview** is the reasoning flagship, with a 1M-token input window and a three-tier thinking control that trades latency against reasoning depth. Suited to very large documents and mixed-media source material processed in a single pass.
**Gemini 2.5 Pro** remains stable and available. **Gemini 3 Pro Preview** has been superseded in Google's current model list by the 3.1 and 3.x Flash releases; it is retained here for Workflows already benchmarked against it.
Gemini's multimodal input is the differentiator worth designing around: for Document Orders containing diagrams, screenshots, or scanned pages, it reads what text-only models silently skip.
***
## DeepL
Purpose-built neural machine translation rather than a general-purpose LLM, across **240+ languages and variants** — the widest language coverage in the catalog.
| Model | Provider tag | Order types | Status |
| -------------- | ---------------- | ------------------ | ------------ |
| DeepL | `deepl` | Document, Subtitle | Available |
| DeepL Extended | `deepl_extended` | Document, Subtitle | Experimental |
DeepL is the one family in this catalog that does **not** serve AI Dubbing Orders. Dubbing scripts need timing-aware, speakable output, which is outside what a pure NMT engine produces.
DeepL is more steerable than "NMT" suggests. Its API supports **glossaries** (up to five per request), **translation memory** with adjustable matching thresholds, **style rules**, **formality** control, XML and HTML **tag handling**, a **context** parameter for text that influences the translation without being translated, and **custom instructions** — up to ten per request, 300 characters each. A `model_type` parameter selects between quality-optimized and latency-optimized behavior.
Document translation preserves formatting across **docx, pptx, xlsx, pdf, html, txt, xliff, srt, idml, xml, json, dita,** and **mif**.
**DeepL Extended** adds translation of **images embedded inside documents** — the difference between a translated PDF whose diagrams are still in the source language and one that is genuinely localized.
***
## Amazon Translate
Neural machine translation across **75 languages and variants**, with the enterprise controls that come with AWS.
| Model | Provider tag | Order types |
| ---------- | ------------ | ------------------------------ |
| Amazon AWS | `aws` | Document, Subtitle, AI Dubbing |
Its case rests on four output controls rather than on model capability: **Custom Terminology**, which forces specific renderings of brand, product, and industry terms; **Active Custom Translation**, which adapts the engine using your own parallel data; **Formality**, which selects register in the languages that support it; and **Brevity**, which constrains output length — genuinely useful for subtitle work, where character limits bind and expansion into a longer target language breaks reading rates. **Profanity masking** is available where content standards require it.
For organizations with a mature translation memory and hard terminology requirements, that combination is often worth more than a higher-capability general model that has to be re-steered on every Order.
***
## Cohere
Enterprise-oriented models built for secure deployment, low latency, and predictable behavior in regulated environments.
| Model | Provider tag | Context | Order types |
| ---------------- | ------------------ | ------- | ------------------------------ |
| Cohere Command-A | `cohere/command-a` | 256K | Document, Subtitle, AI Dubbing |
Command A carries a **256K-token context window** and is built for tool use, agents, retrieval-augmented generation, and multilingual work. It covers the **23 languages of global business**: English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, Chinese, Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, and Persian.
Its strongest fit is **cross-lingual RAG** — pipelines where a translation must be grounded in and traceable to an internal source of truth. Its Arabic, Hebrew, Persian, and Central and Eastern European coverage is a genuine strength relative to models that treat those as long tail.
Cohere also publishes **Command A Translate** (`command-a-translate-08-2025`), a dedicated machine translation model covering the same 23 languages. Ollang's `cohere/command-a` provider runs the general Command A model.
***
## Mistral
| Model | Provider tag | Context | Order types |
| ------------------ | ------------------------------ | ------- | ------------------------------ |
| Mistral Medium 3.1 | `mistralai/mistral-medium-3.1` | 130K | Document, Subtitle, AI Dubbing |
Mistral Medium 3.1 delivers translation and content generation across 50+ languages with a 130K-token context window and multimodal text-plus-image input. Its position here is efficiency — an instruction-following LLM tuned for throughput, which makes it a capable subtitle-translation workhorse for European language pairs.
Mistral has **deprecated Medium 3.1 and 3.2** in favor of **Mistral Medium 3.5** (`mistral-medium-3505`), with retirement dates scheduled through mid-2026. Plan a migration for Workflows that depend on this provider.
***
## Qwen
| Model | Provider tag | Context | Order types |
| ----- | ---------------------- | ------- | ------------------------------ |
| Qwen3 | `qwen/qwen3-235b-a22b` | 262K | Document, Subtitle, AI Dubbing |
Qwen3-235B-A22B is a mixture-of-experts model: **235B total parameters, 22B active per token**, routing across 128 experts with 8 activated at a time.
It carries a **262,144-token native context window** — native rather than extended, so long-document behavior is what the model was trained for — and the Qwen3 family is trained across **119 languages and dialects**. Qwen reports substantial gains in long-tail knowledge coverage across multiple languages, which is the characteristic that matters for translation outside the top 20.
The clearest reason to select it is **Chinese–English** work and long-tail language coverage.
***
## Llama
| Model | Provider tag | Order types |
| ------- | ------------ | ------------------ |
| Llama 4 | `llama` | Document, Subtitle |
Llama 4 does not serve AI Dubbing Orders.
Meta's first natively multimodal, mixture-of-experts open-weight generation. **Scout** runs 17B active parameters across 16 experts (109B total) with a **10M-token context window**; **Maverick** runs 17B active across 128 experts (400B total) with 1M. Both accept multilingual text and images and produce multilingual text and code.
The constraint to design around is that official language support covers only 12 languages: Arabic, English, French, German, Hindi, Indonesian, Italian, Portuguese, Spanish, Tagalog, Thai, and Vietnamese. Outside those, quality falls off sharply against the 100+ language providers. Its knowledge cutoff is also the oldest here, at August 2024.
***
## Related
Pipeline steps, provider tags, and status definitions.
Steer any of these models with glossaries, guidelines, and translation memory.