Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Maritaca AI / Sabiá

Sabiá 3 (December 2024)

Earlier Portuguese language model listed in Maritaca’s December 2025 API documentation. Current access to this revision is unverified.

Language models (LLMs)
historicalClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
7 of 18 specification fields collected
Context window128K128,000 tokens
Maximum outputNot collectedAwaiting source review
Input billingSee ratesMaritaca API (historical)
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
128,000 tokensSource for Context / input limit (opens in a new tab)
Maximum input tokens
Not collected
Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
SupportedSource for Batch processing (opens in a new tab)

Historical Batch API rate was published; this does not establish current endpoint availability.

Fine-tuning
Not collected
Knowledge cutoff
Mid-2023Source for Knowledge cutoff (opens in a new tab)
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
PortugueseSource for Languages (opens in a new tab)

Documented specialization, not a claim that other languages are unsupported.

Context caching
Not collected

No prompt-cache contract verified for this exact historical revision.

API aliases
sabia-3, sabiá-3, sabia-3-2024-12-11, sabiá-3-2024-12-11Source for API aliases (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Maritaca API (historical)

Provider source (opens in a new tab)
API model ID
sabia-3-2024-12-11
Access
Historically listed API; present availability and shutdown date are unverified.
Regions
Not verified for this exact historical deployment.
Equivalent API aliases
sabia-3, sabiá-3, sabia-3-2024-12-11, sabiá-3-2024-12-11Source for Equivalent API aliases (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Dec 2025
CategoryUsageRateUnit
Historical / standardInput1R$5.001M tokens
Historical / standardOutput1R$10.001M tokens
Historical / nightInput1R$3.501M tokens
Historical / nightOutput1R$7.001M tokens
Historical / batchInput1R$2.501M tokens
Historical / batchOutput1R$5.001M tokens

Rate conditions

  1. Historical December 2025 BRL rates, not a current quote. Night hours 22:00–06:00 BRT. No cached-input rate or model-specific shutdown date was collected.
Pricing source (opens in a new tab)

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 INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Maritaca API (historical)

sabia-3-2024-12-11
Not 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.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

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

Named provider model without a matching public weight release in the reviewed official inventory. Classification for historical artifacts is inferred; a public tokenizer, public upstream base or licensed executable is not a public release of this derivative.

Classification evidence (opens in a new tab)

Lifecycle dates

Listed in official API documentation15 Dec 2025Source (opens in a new tab)

Sources reviewed