Cognition

Developer of SWE software-engineering models, including the Windsurf-origin family, deployed through Devin products and specialized coding tools.

Eleven named SWE checkpoints reviewed across coding, retrieval and bug detection. Serving speeds, effort levels and account billing tiers are access variants. Historical Codeium/Windsurf models, research prototypes and remaining exact-version contracts still need 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.

11 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	Inline additions/deletions, imports and predicted next edit locations.output formats	Usage pricingNot collected		Needs rate detailsPrice details ↗
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	$0.50/ 1M tokensPublished Self-serve rates	$2.50/ 1M tokens	$0.00175Devin · SWE-1.6 · Self-servePrice details ↗
Not collected	Not collected	$0.00/ 1M tokensSelf-serve: no token charge listed	$0.00/ 1M tokens	$0.00Devin · SWE-1.7 Medium · Self-servePrice details ↗
Not collected	Not collected	$3.00/ 1M tokensPublished list rates	$15.00/ 1M tokens	$0.0105Devin · SWE-2 High · Self-servePrice details ↗
Not collected	Relevant source file paths and line ranges, rather than embedding vectors.output formats	Usage pricingNot collected		Needs rate detailsPrice details ↗
Not collected	Relevant source file paths and line ranges, rather than embedding vectors.output formats	Usage pricingNot collected		Needs rate detailsPrice details ↗
Not collected	Structured bug descriptions and suggested fixes for the current code diff.output formats	Usage pricing $0.00 / reviewSWE-check review · Devin Desktop · Quick ReviewRates & conditions ↗		No text-only estimatePrice 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