Specialized translation LLM family accessed through managed text and document APIs. Speed and quality preferences guide routing across models rather than choosing a fixed checkpoint.
126 language/variant entries in the current documentation table, not 126 separately named models. Use /v3/languages for resource-specific source/target availability.
Paid Growth/Enterprise managed text translation. Authenticate with Authorization: DeepL-Auth-Key. Selector values are routing preferences, not model IDs.
Regions
Provider-managed; contractual residency options, no universal region pin
Entire text request including optional context; this is a byte limit, not a token or character window. Header limit: 16 KiB.
Model routing
Default latency_optimized; quality_optimized and legacy prefer_quality_optimized are equivalent quality preferences; model_type_used reports the chosen modeSource for Model routing (opens in a new tab)
Opt-in alpha: up to 10 source/target examples, each side at most 300 characters. English paired with German, Spanish, French or Italian. JSON requests only.Source for Adaptive translation (opens in a new tab)
Examples are resubmitted per request and not stored. Best-effort adaptation may have no visible effect; this is not a fine-tuning API.
No discounted prompt-cache rate inferred from translation-memory reuse.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Language API usage
Growth text translation overage1
$27.50
1M additional source characters
Subscription
Growth shared subscription2
$26.00
month, billed annually
Rate conditions
Native India/USD price view, annual billing selected: Growth is $26/month billed annually, with 12M characters, 120 STT hours and 60 S2S hours per year. Usage above those allowances is extra. This is a shared account plan, not an extra subscription for every model/endpoint. 50M characters and 300 voice hours/month limits; Enterprise is custom. $27.50 per million additional characters, not tokens. Unicode code points of source text are billed; output tokens have no separately collected price. Document minimums and beta exceptions apply.
Native India/USD price view, annual billing selected: Growth is $26/month billed annually, with 12M characters, 120 STT hours and 60 S2S hours per year. Usage above those allowances is extra. This is a shared account plan, not an extra subscription for every model/endpoint. 50M characters and 300 voice hours/month limits; Enterprise is custom.
Paid Growth API advertises no data training. Terms allow temporary processing storage, encrypted exceptional debugging retention up to 72 hours, and metadata logs. Customer-requested stored content has separate deletion terms. Region is not universally fixed; enterprise residency requires agreement. Free Developer terms differ.
Columns are format, free-plan limit, paid-plan limit. Paid DOC/DOCX/PPTX/PDF up to 100 MB and 1M characters; other formats differ. Service specification still lists 30 MB for those formats, a documented conflict.
Document billing
At least 50,000 source characters billed for DOC/DOCX/PPTX/XLSX/PDF; beta formats currently unbilled. All document content counts, including untranslated parts.Source for Document billing (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Language API usage
Growth document translation overage1
$27.50
1M additional source characters
Rate conditions
Native India/USD price view, annual billing selected: Growth is $26/month billed annually, with 12M characters, 120 STT hours and 60 S2S hours per year. Usage above those allowances is extra. This is a shared account plan, not an extra subscription for every model/endpoint. 50M characters and 300 voice hours/month limits; Enterprise is custom. $27.50 per million additional characters, not tokens. Unicode code points of source text are billed; output tokens have no separately collected price. Document minimums and beta exceptions apply. Minimum 50,000 characters for DOC/DOCX/PPTX/XLSX/PDF; beta formats currently exempt.
Paid Growth API advertises no data training. Terms allow temporary processing storage, encrypted exceptional debugging retention up to 72 hours, and metadata logs. Customer-requested stored content has separate deletion terms. Region is not universally fixed; enterprise residency requires agreement. Free Developer terms differ.
No public fixed model/checkpoint selector is documented.
Access
Current Developer plan: one-time 1M-character credit, one API key, one glossary and one style list. Verify the base URL supplied with the account; legacy API Free uses api-free.deepl.com.
Regions
Provider-managed; contractual residency options, no universal region pin
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Developer terms section 3.3.2 reserve the right to store content and processed content perpetually. Do not inherit the paid Growth no-training/temporary-storage claims.
No public fixed model/checkpoint selector is documented.
Access
DeepL-managed API purchased through AWS Marketplace. Not an Amazon foundation model or a separate checkpoint.
Regions
Provider-managed; contractual residency options, no universal region pin
Pricing discrepancy
Character overage shows $27.5/M in its dimension, $25/M in its description and $0.00000275 per character in the cost field. These disagree; confirm the offer before using an overage estimate.Source for Pricing discrepancy (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Contract
Growth bundle1
$312.00
12-month contract
Contract
Enterprise bundle2
$15,000.00
12-month contract
Rate conditions
12M characters + 120 STT hours + 60 S2S hours per year. Additional usage is separate. Current listing has inconsistent overage dimensions/descriptions, so no numeric overage rate is asserted.
600M characters + 240 STT hours + 60 S2S hours per year, plus enterprise features. Additional usage is separate; private terms may differ.
Paid Growth API advertises no data training. Terms allow temporary processing storage, encrypted exceptional debugging retention up to 72 hours, and metadata logs. Customer-requested stored content has separate deletion terms. Region is not universally fixed; enterprise residency requires agreement. Free Developer terms differ.
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How it works
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Minimum reusable input
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Lifetime & refresh
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How to enable it
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Usage fields
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Billing rules
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Limits & data boundaries
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
DeepL API
Not verified
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How it works
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Minimum reusable input
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Lifetime & refresh
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How to enable it
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Usage fields
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Billing rules
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Limits & data boundaries
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
DeepL API
Not verified
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How it works
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Minimum reusable input
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Lifetime & refresh
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How to enable it
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Usage fields
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Billing rules
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Limits & data boundaries
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
DeepL · AWS Marketplace
Not verified
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How it works
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Minimum reusable input
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Lifetime & refresh
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How to enable it
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Usage fields
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Billing rules
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Limits & data boundaries
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
DeepL terms identify proprietary models and restrict copying or reverse engineering of the service. This is a documented proprietary generation or explicitly identified managed/research family, not a claim that every hosted partner component is a DeepL checkpoint. Public model weights are not provided by the cited release or API documentation.
