Maritaca AI / Sabiá
Historical Portuguese model revision explicitly discontinued in Maritaca’s API retirement table.
Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
The named September/November revisions were evaluated on BFCL function calling. Current endpoint is retired.
Documented specialization, not a claim that other languages are unsupported.
No prompt-cache contract verified for this exact historical revision.
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
sabia-3-2024-09-09Endpoint pricing has not been collected. Check the provider for applicable rates.
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
The system processes eligible input and retains reusable state.
Reuse depends on matching input, session state and the cache policy.
Reusing state can reduce repeated work. Any charges follow the billing rules below.
sabia-3-2024-09-09No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026Provider technical report revision 2 identifies the September 9 Sabiá 3 and November 13 Sabiazinho 3 checkpoints. Exams average 70 tests after mid-2023. BFCL uses English examples. AgentBench uses inverse-difficulty weights and a 0–10 normalized overall score. These are not results for December 2024 / February 2025 revisions.
Evaluation source (opens in a new tab)Provider technical report revision 2 identifies the September 9 Sabiá 3 and November 13 Sabiazinho 3 checkpoints. Exams average 70 tests after mid-2023. BFCL uses English examples. AgentBench uses inverse-difficulty weights and a 0–10 normalized overall score. These are not results for December 2024 / February 2025 revisions.
Evaluation source (opens in a new tab)Provider technical report revision 2 identifies the September 9 Sabiá 3 and November 13 Sabiazinho 3 checkpoints. Exams average 70 tests after mid-2023. BFCL uses English examples. AgentBench uses inverse-difficulty weights and a 0–10 normalized overall score. These are not results for December 2024 / February 2025 revisions.
Evaluation source (opens in a new tab)Provider technical report revision 2 identifies the September 9 Sabiá 3 and November 13 Sabiazinho 3 checkpoints. Exams average 70 tests after mid-2023. BFCL uses English examples. AgentBench uses inverse-difficulty weights and a 0–10 normalized overall score. These are not results for December 2024 / February 2025 revisions.
Evaluation source (opens in a new tab)Provider technical report revision 2 identifies the September 9 Sabiá 3 and November 13 Sabiazinho 3 checkpoints. Exams average 70 tests after mid-2023. BFCL uses English examples. AgentBench uses inverse-difficulty weights and a 0–10 normalized overall score. These are not results for December 2024 / February 2025 revisions.
Evaluation source (opens in a new tab)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.
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)