Contextual AI

Specialized grounded language models, instruction-following retrieval and managed document-understanding components for enterprise RAG.

Two GLM API versions, original v1 reranker and two managed components reviewed. Public LMUnit and Reranker v2 weights are excluded. Earlier family identities, tuned variants and unpublished cache contracts remain open.

Closed-weight models

Browse by model typeCapabilities can overlap

Start with the job your model needs to do. Then narrow by capabilities, provider and price.

Select up to 3 models to compare

What does one question cost?

Compare every model with the same request.

Input tokensOutput tokens

Estimate = (input tokens × input price + output tokens × output price) / 1,000,000. Include conversation history in input and billed reasoning in output. Input-only decision models ignore the output setting; enter all billed input for one decision, including its question and criteria. Media, tools and discounts are separate.

5 models

Sort by

Model input and output limits, prices and estimated cost per question at the selected token counts.
Input tokensPublished limit*	Output tokensMaximum per response*	Input pricePer 1M tokens	Output pricePer 1M tokens	Cost per question1,000 input + 500 outputEstimated · uncached
32,000max input tokens	2,048max output tokens	$3.00/ 1M tokensStandard rates	$15.00/ 1M tokens	$0.0105Contextual AI APIPrice details ↗
32,000max input tokens	2,048max output tokens	$3.00/ 1M tokensStandard rates	$15.00/ 1M tokens	$0.0105Contextual AI APIPrice details ↗
Not collected	Not collected	Usage pricingNot collected		Different billing unitPrice details ↗
Less than 2,000 pages; Office-to-PDF conversion can change page count.document page limits	markdown-document, markdown-per-page, blocks-per-pageoutput formats	Usage pricing $3.00 / 1,000 pagesBasic pages · Contextual AI API$40.00 / 1,000 pagesStandard pages · Contextual AI APIRates & conditions ↗		Task-based pricingPrice details ↗
Not collected	Not collected	Usage pricingNot collected		Task-based pricingPrice details ↗

* Media models show their native limits. A shared context window includes both input and output tokens.

Original currency and billing unit, without currency conversion. Rates are dated snapshots; open the conditions for tiers, promotions and endpoint restrictions.How to read the data

Catalog coverage

Closed-weight model variants and explicitly identified closed-source managed model components across language, code, image, video, audio and other documented modalities. Global provider and historical-release coverage is being expanded; this is not yet exhaustive. 172 company reviews are still open.

See what is being reviewed