--- title: "Maritaca AI Academic Credits free inference" description: "No-cost research and development inference across 10 models; not unrestricted production use." canonical_url: "https://freeinferencing.com/provider/maritaca_academic_credits/" md_url: "https://freeinferencing.com/provider/maritaca_academic_credits.md" last_updated: "2026-09-19" --- # Maritaca AI Academic Credits > No-cost research and development inference across 10 models; not unrestricted production use. ## Classification - **Directory:** Current - **Free access:** Research / development - **Status:** Restricted access - **Confidence:** High - **Payment card:** Unknown - **Account:** Not documented - **Equivalent paid value:** At least R$36,817.20/mo - **API endpoint:** `https://chat.maritaca.ai/api` ## Models mentioned - `sabia-4` - `sabia-4-br-sp` - `sabia-4-thinking` - `sabia-4-thinking-br-sp` - `sabiazinho-4` - `sabiazinho-4-br-sp` - `sabia-4-2026-01-06` - `sabiazinho-4-2026-01-06` - `sabia-4-small` - `sabiazim-4` ## Limits and terms ```yaml credit_amount: not_public duration: not_public tier_0_requests_per_minute: 60 tier_0_input_tokens_per_minute: 128000 tier_0_output_tokens_per_minute: 10000 ``` ## What happens to your prompts? **Private.** The API DPA says prompts and outputs are immediately discarded and never used for training or improvement; only narrow technical logs and temporary error fragments remain. Privacy is audited separately from price. Review the current governing terms before sending sensitive or regulated data. ## Data governance and agreements ```yaml data_governance: review_status: reviewed plan_scope: Maritaca hosted API, including approved academic-credit use; the public API DPA applies automatically. prompt_retention: API prompts are processed for inference and immediately discarded after the response, subject only to narrow temporary error fragments. response_retention: API outputs are immediately discarded after delivery under the same DPA rule. ordinary_logging: Technical logs without ordinary prompt/output content may be kept for up to 18 months; error fragments may be retained for up to 30 days for diagnosis. model_training: Maritaca says API prompts and outputs are never used to train models. product_improvement: API prompts and outputs are excluded from content-based service improvement. human_or_operator_access: Ordinary content is not retained for review; authorized staff may access narrow error fragments during their 30-day diagnostic window. subprocessors_and_routing: The DPA governs Maritaca and disclosed processors; the qualifying Sabiá API is operated by Maritaca rather than an arbitrary model router. deletion_controls: Ordinary content is discarded automatically. Technical records and error fragments expire under their stated 18-month and 30-day limits, with data-subject controls supplied by the DPA. caveat: The narrow error-fragment exception should still be considered before sending regulated or confidential data. agreements: data_processing_agreement: https://www.maritaca.ai/dpa/ ``` ## Eligibility ```yaml application_required: true applicants: - students - faculty - researchers project_types: - teaching - scientific_research ``` ## API compatibility and modalities - **Compatibility:** OpenAI Compatible - **Modalities:** Text generation - **Geography:** Brazil ## Before you build with Maritaca AI Academic Credits ### Read the classification narrowly This record describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every account and region. “Research / development” should be interpreted together with the Current directory placement, High confidence, Unknown payment-card status, and the plan-specific sources below. ### Resolve the live model route The snapshot records 10 model IDs. Match the exact ID against the provider's current catalog before using it in code because zero-price routes, aliases, context limits, and feature support can rotate while an older documentation page remains online. ### Match the quota to the workload shape Translate the allowance into peak requests per minute, input and output tokens, concurrency, retries, and every daily or monthly ceiling that applies to the intended account. The first limit reached by the workload is the practical ceiling. A large token pool can still fail interactive bursts, and a high request limit can still fail long-context work. Include tool calls and retry traffic, test the largest realistic payload, and treat research, experimental, and community access as conditional on their eligibility and fair-use terms. ### Preserve billing and privacy boundaries The recorded payment-card requirement is Unknown, and account access is not documented. Confirm both in the live signup flow, set provider-side budgets when charges are possible, and observe the balance or usage fields after a complete request. The prompt-handling classification is **Private** because The API DPA says prompts and outputs are immediately discarded and never used for training or improvement; only narrow technical logs and temporary error fragments remain. Re-read the terms for the exact route and plan before sending sensitive, regulated, or proprietary content. ### Follow the evidence, then re-check it This record links 7 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest and most specific governing document or live catalog when sources disagree. A dated finding can become stale even when the page remains online, so retain the source and snapshot that supported the decision and submit a correction when a provider changes a material term. ### Plan fallback without policy drift A fallback should preserve modality, context length, streaming, structured output, tools, safety controls, and data terms, not only API syntax. Decide which errors may retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. Rotating aliases and free pools can change behavior without changing the endpoint, so retain the response model field and test at least one substitute route before the primary offer becomes unavailable. ### Monitor the offer as a dependency Capture the model ID, response model, rate-limit headers, usage fields, latency, HTTP status, and provider request identifier. Watch authorization failure, quota exhaustion, catalog removal, policy revision, and balance movement as separate failure modes. Re-check the live catalog and governing sources on a schedule proportionate to the workload's importance, and keep an owner and exit path for any production dependency on volatile free capacity. ### Test one complete request before scaling Start with the smallest permitted request using the exact credential, model ID, endpoint, region, and account type intended for deployment. Record the status, headers, usage fields, response model, latency, and dashboard balance movement. Then exercise an invalid model, quota exhaustion, or rate limit so failure is explicit and cannot silently switch to a paid route. Validate streaming, structured output, and tool calls separately because a free model can expose fewer features than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and do not send sensitive data until the observed route matches the reviewed agreement. ## Primary sources - [Academic credits](https://www.maritaca.ai/research): Official Program - [Models](https://docs.maritaca.ai/pt/modelos): Official Catalog - [Rate limits](https://docs.maritaca.ai/pt/rate-limits): Official Docs - [Pricing](https://docs.maritaca.ai/pt/precos): Official Pricing - [Data Processing Agreement](https://www.maritaca.ai/dpa/): Official Data Processing Agreement - [maritaca-ai/maritalk-api official API client repository](https://github.com/maritaca-ai/maritalk-api): Official Repository - [PyPI download stats for maritalk](https://pypistats.org/packages/maritalk): Package Registry Stats ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.