Cursor

Developer-tool provider training the Composer coding-model family and custom completion models. Hosted third-party models retain their original provider identities.

Four Composer generations and one managed Tab record reviewed. Historical prices, standard/fast serving tiers and raw-model versus agent APIs remain distinct. Internal prototypes, older completion models and exact runtime contracts require further review.

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
Not collected	Not collected	Usage pricingNot collected		Needs rate detailsPrice details ↗
Not collected	Not collected	Usage pricingNot collected		Needs rate detailsPrice details ↗
Not collected	Not collected	Historical pricing $0.50 / 1M tokensInput tokens · Cursor Composer 2 · standard$2.50 / 1M tokensOutput tokens · Cursor Composer 2 · standardRates & conditions ↗		No text-only estimatePrice details ↗
200,000context tokens	Not collected	$0.50/ 1M tokensStandard rates	$2.50/ 1M tokens	$0.00175Cursor Composer 2.5 · standardPrice details ↗
Not collected	Inline code suggestions, multiline changes, imports and cross-file next-edit locations.output formats	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