Research family being developed to translate directly from speech to speech without an intermediate transcription. Public checkpoint names and a production API mapping are not disclosed.
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 AI Labs
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.
