A redirected request no longer proves access to the original model. This is routing history, not a second name for identical weights.
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.
Cohere Generate API (historical version)
small-20220926
Not verified
No historical version-specific cache policy verified.
How it works
Not collected
No historical version-specific cache policy verified.
Minimum reusable input
Not collected
No historical version-specific cache policy verified.
Lifetime & refresh
Not collected
No historical version-specific cache policy verified.
How to enable it
Not collected
No historical version-specific cache policy verified.
Usage fields
Not collected
No historical version-specific cache policy verified.
Billing rules
Not collected
No historical version-specific cache policy verified.
Limits & data boundaries
Not collected
No historical version-specific cache policy verified.
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
Historical distribution inference: the original provider announcement identifies this dated model as a Cohere API/Playground offering and distinguishes it from earlier versions. Reviewed distribution evidence offers managed access, not downloadable original weights. Public tokenizers or later public Command R/A weights do not establish an open release of this original version.