DeepL
Specialist language AI for translation, writing, speech and translation-quality evaluation. Its managed API routes requests among proprietary models.
Current translation, Write, Voice and evaluation services, the classic generation and direct speech research reviewed. Internal language-specific checkpoint names are not publicly enumerated; partner speech systems and historical model versions remain under review.
Start with the job your model needs to do. Then narrow by capabilities, provider and price.
Compare every model with the same request.
Estimate = (input tokens × input price + output tokens × output price) / 1,000,000. Include conversation history in input and billed reasoning in output. Input-only decision models ignore the output setting; enter all billed input for one decision, including its question and criteria. Media, tools and discounts are separate.
7 models
| Compare | Model | Input tokensPublished limit* | Output tokensMaximum per response* | Input pricePer 1M tokens | Output pricePer 1M tokens | Cost per question1,000 input + 500 outputEstimated · uncached |
|---|---|---|---|---|---|---|
| Not collected | Not collected | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 128 KiBrequest body limit | Translated text; translated documents in supported source formats, with DOC→DOCX and optional PDF→DOCXoutput formats | Usage pricing $27.50 / 1M additional source charactersGrowth text translation overage · DeepL API$26.00 / month, billed annuallyGrowth shared subscription · DeepL APICharacter billing, with included plan allowances; document minimums differ by formatRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 10 KiBrequest body limit | Improved text with detected source and target language fieldsoutput formats | Usage pricing $27.50 / 1M additional source charactersGrowth Write overage · DeepL APISource characters count in the shared Translate + Write quotaRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 3 hours per recorded jobaudio limit | Transcripts, translated text and optional synthesized speech; recorded jobs also support SRT captionsoutput formats | Usage pricing $1.85 / additional source audio hourGrowth speech-to-text overage · DeepL API$3.75 / additional source audio hourGrowth speech-to-speech overage · DeepL APINative Growth overages: $1.85/STT hour and $3.75/S2S hour after plan allowancesRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| Not collected | Language code on success; otherwise insufficient_confidence, unsupported_language or no_language_detectedoutput formats | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 10,000 combined per segmenttext input | Per-segment score (0–100), issues, severity, explanations and Unicode code-point spans; optional glossary term pairsoutput formats | Usage pricing Separate evaluation-character quota; no public numeric tariff collectedRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
* Media models show their native limits. A shared context window includes both input and output tokens.
Catalog coverage
Closed-weight model variants and explicitly identified closed-source managed model components across language, code, image, video, audio and other documented modalities. Global provider and historical-release coverage is being expanded; this is not yet exhaustive. 172 company reviews are still open.
See what is being reviewed