Retired Enterprise/Vertex AI release; the API selector is recorded for historical identification, not as an active endpoint.
Regions
Historical model-specific availability not collected
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Caching
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.
Google Enterprise Agent Platform / Vertex AI (historical)
gemini-1.5-pro-002
Not verified
No verified historical cache policy for this selector; current Gemini caching is not inherited.
How it works
Not collected
No verified historical cache policy for this selector; current Gemini caching is not inherited.
Minimum reusable input
Not collected
No verified historical cache policy for this selector; current Gemini caching is not inherited.
Lifetime & refresh
Not collected
No verified historical cache policy for this selector; current Gemini caching is not inherited.
How to enable it
Not collected
No verified historical cache policy for this selector; current Gemini caching is not inherited.
Usage fields
Not collected
No verified historical cache policy for this selector; current Gemini caching is not inherited.
Billing rules
Not collected
No verified historical cache policy for this selector; current Gemini caching is not inherited.
Limits & data boundaries
Not collected
No verified historical cache policy for this selector; current Gemini caching is not inherited.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
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
Google documents this original proprietary hosted model/version in its lifecycle and release material. No downloadable weights are supplied. Records identify named releases, not claims about exact weights or architecture shared across aliases or hosts.
