Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Per query/document pair. Long documents may be chunked; this is not a chat-generation context window.
Provider-reported language coverage; performance varies by language and task.
See endpoint caching records. No verified support claim for this model.
Longer queries are truncated to this token count; query and document share the model context window.
Version-specific controls: v1 details are documented in the separately linked v1 API. The default v2 truncation setting is not the model context length.
v2 removed document-object arrays. Preserve YAML field order because long strings can be truncated.
This fixed API response does not imply general-purpose JSON-schema constrained generation.
The recommendation is not an enforced 1,000-document ceiling. Best-practices and v1 reference differ on the equality boundary and default chunk count; check the selected transport.
This service lifecycle notice does not establish whether custom enterprise contracts can provide a different deployment arrangement.
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
rerank-v4.0-proEndpoint pricing has not been collected. Check the provider for applicable rates.
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Not collectedPrices retain their published currencies and billing units below.
| Category | Usage | Rate | Unit |
|---|---|---|---|
| Dedicated inference · Medium | Hourly1 | $5.00 | instance-hour |
| Dedicated inference · Medium | Monthly1 | $3,250.00 | instance-month |
| Dedicated inference · Large | Hourly2 | $10.00 | instance-hour |
| Dedicated inference · Large | Monthly2 | $6,500.00 | instance-month |
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
The system processes eligible input and retains reusable state.
Reuse depends on matching input, session state and the cache policy.
Reusing state can reduce repeated work. Any charges follow the billing rules below.
rerank-v4.0-proProvider-side caching has not been verified for this endpoint. Missing documentation is not evidence that caching is unsupported.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Provider-side caching has not been verified for this endpoint. Missing documentation is not evidence that caching is unsupported.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
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 provider explicitly labels this exact model Proprietary, separately from families with public weight downloads.
Classification evidence (opens in a new tab)