Independent evaluation model that checks DeepL translations segment by segment and directs human reviewers to possible meaning, fluency and style issues.
DE → EN-GB, EN-US, EN → DE, ES, ES-419, FR, IT, JA, KO, ES → EN-GB, EN-US, FR → EN-GB, EN-US, IT → EN-GB, EN-US, JA → EN-GB, EN-US, KO, ZH-HANS, ZH-HANT, KO → EN-GB, EN-US, JA, ZH → JASource for Languages (opens in a new tab)
Combined source + target length. Larger segments receive InternalTQEError / SegmentTooLarge and are not evaluated; remaining segments continue. Not a full-document limit.
No public fixed model/checkpoint selector is documented.
Access
Selected customers only, enabled by a customer success manager. No public standalone evaluation-start endpoint; evaluate a translation produced in a document job.
Regions
Provider-managed; contractual residency options, no universal region pin
DE → EN-GB, EN-US, EN → DE, ES, ES-419, FR, IT, JA, KO, ES → EN-GB, EN-US, FR → EN-GB, EN-US, IT → EN-GB, EN-US, JA → EN-GB, EN-US, KO, ZH-HANS, ZH-HANT, KO → EN-GB, EN-US, JA, ZH → JASource for Languages (opens in a new tab)
Combined source + target length. Larger segments receive InternalTQEError / SegmentTooLarge and are not evaluated; remaining segments continue. Not a full-document limit.
0–100 quality score, not probability; Critical/Major/Minor issue severity. Source/target spans are half-open Unicode code-point offsets into returned segment strings.Source for How to interpret scores (opens in a new tab)
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Reports retained for 24 hours after done or error, then return 404. They are scoped to the requesting account; an ID from another account also returns 404.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
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.
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.
