/ IBM / Granite 13B Chat V2 (2.1.0) IBM / Granite
Granite 13B Chat V2 (2.1.0) IBM’s conversation and RAG adaptation of the proprietary 2.5T-token Granite 13B base.
available Closed weights Text generation
Context window 8.2K 8,192 tokens
Maximum output Not collected Awaiting source review
Input billing See billing notes IBM watsonx.ai dedicated deployment
Output billing See billing notes Access and billing notes below
Specifications Access & pricing Caching Evaluation Sources & lifecycle
Specifications Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Maximum output Not collected
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
Context caching Not collected Published price Dedicated model hosting; no pay-as-you-go token rate listedSource for Published price (opens in a new tab) Hosting is billable. No numeric GPU-hour tariff was verified in this review; no per-question token price is inferred.
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 ibm/granite-13b-chat-v2-curatedCurated catalog identifier, not a drop-in shared text-generation request selector.
Access Deploy on demand on dedicated hardware. The catalog selector provisions a deployment; inference uses that deployment’s route. Shared pay-as-you-go retirement does not imply this deployment is retired.
Regions Product, deployment, and region restrictions apply. This record does not imply global availability or residency. 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 INPUT Process & retain The system processes eligible input and retains reusable state.
02 / LATER REQUEST Check available state Reuse depends on matching input, session state and the cache policy.
03 / CACHE HIT Reuse & generate Reusing state can reduce repeated work. Any charges follow the billing rules below.
IBM watsonx.ai dedicated deployment ibm/granite-13b-chat-v2-curatedNot verified
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
MMLU (5-shot) IBM · vendor-reported 57% IBM model card, checkpoint revision 2.1.0; five-shot evaluation. Do not apply this score to the original 2.0.0 alignment.
Evaluation source (opens in a new tab)
MT-Bench IBM · vendor-reported 6.92score IBM model card, checkpoint revision 2.1.0. Vendor-reported multi-turn evaluation, not a live independent ranking.
Evaluation source (opens in a new tab) 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 IBM documents this proprietary product or research checkpoint. Closed-weight status applies to this exact release, not to all Granite models. Public IBM Granite and IBM Research weight inventories were reviewed separately; newer public-weight releases are excluded.
Classification evidence (opens in a new tab) Lifecycle dates Sources reviewed 