Skip to content
Model infoModelsSnapshot: 15 Oct 2026

NAVER Cloud / CLOVA RAG

CLOVA Reranker

Native document selection and answer generation model service. It returns an answer with cited documents, rather than just a list of relevance scores.

availableClosed weightsRerankingText generation
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
5 of 18 specification fields collected
Input token limit128K128,000 tokens
Maximum output4.1K4,096 tokens
Input billingNot collectedCLOVA Studio
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
4,096 tokensSource for Maximum output (opens in a new tab)

The prose states a 4,096-token ceiling, but the request parameter table uses maxTokens < 4096. Check the live API boundary before relying on an inclusive maximum.

Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected
Request mode
Dedicated API route; the underlying checkpoint identifier is not exposed.Source for Request mode (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

API model ID
Not collected

The dedicated service route does not expose a model selector.

Access
NAVER Cloud account and CLOVA Studio API key required. Native documentation lists Classic and VPC availability; no paid inference call was made.
Regions
Account and contract dependent; the common API hostname alone does not prove data residency.
API endpoint URL
POST https://clovastudio.stream.ntruss.com/v1/api-tools/rerankerSource for API endpoint URL (opens in a new tab)
Request limits
Web/test: 60 requests/min, 45,000 tokens/min. Production: 120 requests/min, 180,000 tokens/min.Source for Request limits (opens in a new tab)

Published quota snapshot, not guaranteed throughput. Usage is aggregated by main account, including subaccounts; tuned models share the base model quota. Token accounting includes input plus reserved maximum output where applicable.

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.

CLOVA Studio

Not verified

The reviewed model and API guides do not establish provider-side prompt caching for this model. Missing documentation is not evidence of no support.

How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

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

Inferred for this exact named NAVER native commercial model/service from its official API documentation and comparison with the public HyperCLOVA X SEED inventory. No public weights for this exact service were found in the reviewed sources. This does not establish that every NAVER service is closed; BGE-M3 and public SEED releases are excluded.

Classification evidence (opens in a new tab)

Lifecycle dates

Service released17 Jul 2025Source (opens in a new tab)

Sources reviewed