Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Maritaca AI

Brazilian developer of Sabiá language models, specializing in Portuguese and Brazilian knowledge, with API access and optional São Paulo processing.

Sabiá 4 Thinking, Sabiá 4 and Sabiazinho 4 with standard and BR-SP endpoints, plus named earlier Sabiá research models and historical API revisions. Public Sabiá 7B weights, tokenizers, regional aliases and application names are not extra closed models.

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.

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.

13 models

Model input and output limits, prices and estimated cost per question at the selected token counts.
CompareModelInput tokensPublished limit*Output tokensMaximum per response*Input pricePer 1M tokensOutput pricePer 1M tokensCost per question1,000 input + 500 outputEstimated · uncached
1,000,000context tokens32,768max output tokensR$5.00/ 1M tokensStandard ratesR$40.00/ 1M tokensR$0.025Maritaca APIPrice details ↗
128,000context tokens32,768max output tokensR$5.00/ 1M tokensStandard ratesR$20.00/ 1M tokensR$0.015Maritaca APIPrice details ↗
128,000context tokens32,768max output tokensR$1.00/ 1M tokensStandard ratesR$4.00/ 1M tokensR$0.003Maritaca APIPrice details ↗
128,000context tokensNot collectedHistorical pricing
R$5.00 / 1M tokensInput · Maritaca API (historical)R$10.00 / 1M tokensOutput · Maritaca API (historical)Rates & conditions ↗
No text-only estimatePrice details ↗
128,000context tokensNot collectedHistorical pricing
R$5.00 / 1M tokensInput · Maritaca API (historical)R$10.00 / 1M tokensOutput · Maritaca API (historical)Rates & conditions ↗
No text-only estimatePrice details ↗
32,000context tokensNot collectedHistorical pricing
R$1.00 / 1M tokensInput · Maritaca API (historical)R$3.00 / 1M tokensOutput · Maritaca API (historical)Rates & conditions ↗
No text-only estimatePrice details ↗
Not collectedNot collectedUsage pricingNot collectedNeeds rate detailsPrice details ↗
32,000context tokensNot collectedUsage pricingNot collectedNeeds rate detailsPrice details ↗
32,000context tokensNot collectedUsage pricingNot collectedNeeds rate detailsPrice details ↗
Not collectedNot collectedUsage pricingNot collectedNeeds rate detailsPrice details ↗
Not collectedNot collectedUsage pricingNot collectedNeeds rate detailsPrice details ↗
Not collectedNot collectedUsage pricingNot collectedNeeds rate detailsPrice details ↗
Not collectedNot collectedUsage pricingNot collectedNeeds rate detailsPrice 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