--- title: "Google Cloud Vertex AI free inference" description: "$300 for new accounts; it does not recur. See verified limits, model IDs, privacy terms, and primary sources for Google Cloud Vertex AI." canonical_url: "https://freeinferencing.com/provider/google_vertex_ai/" md_url: "https://freeinferencing.com/provider/google_vertex_ai.md" last_updated: "2026-09-19" --- # Google Cloud Vertex AI > $300 for new accounts; it does not recur. ## Classification - **Directory:** Current - **Free access:** One-time trial - **Status:** Current trial - **Confidence:** High - **Payment card:** Yes - **Account:** Not documented - **Equivalent paid value:** $300.00 once - **API endpoint:** `https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/google/models/{model}:generateContent` ## Models mentioned No stable model IDs were recorded in this snapshot. ## Limits and terms ```yaml general_cloud_credit_usd: 300 duration_days: 90 recurrence: false ``` ## What happens to your prompts? **Partially private.** Google Cloud excludes training without permission, but caching, grounding, and session features introduce bounded retention. 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: Generative AI on Vertex AI, including managed Google and partner models; grounding, caching, live sessions, stateful resources, and abuse-monitoring eligibility differ. prompt_retention: Stateless inference is not retained at rest by default, but Gemini uses project-isolated in-memory caching for up to 24 hours unless disabled. Grounding with Google Search or Maps stores prompts, context, and outputs for 30 days; session resumption caches content up to 24 hours. response_retention: Same feature-specific handling as prompts. Explicit context caches, batch files, tuned models, RAG stores, and other customer resources persist until their configured expiry or deletion. ordinary_logging: Some customers under Google Cloud Platform Terms are subject to prompt logging for abuse monitoring and can request an exception. Service, billing, and security metadata remains. model_training: Google contractually says it will not use customer data to train or fine-tune any AI/ML model without prior permission or instruction, including GA and pre-GA managed models. product_improvement: Customer content is excluded from general model improvement absent permission; grounding data may be used for debugging and testing the grounding systems during its 30-day retention. human_or_operator_access: Abuse and support access follows Google Cloud controls and Access Transparency where available; no universal operator-blind commitment applies to every free or feature path. subprocessors_and_routing: Google Cloud and its subprocessors process data in the configured region or multi-region, while partner models and grounding services can add separate terms and locations. deletion_controls: Customers can disable in-memory caching, request an abuse-monitoring exception where eligible, avoid stored grounding/session features, and delete explicit caches and other Vertex resources. caveat: Vertex AI's no-training promise is strong, but achieving zero retention requires disabling or avoiding every documented cache, grounding, session, abuse, and stateful-storage path. agreements: cloud_terms: https://cloud.google.com/terms service_specific_terms: https://cloud.google.com/terms/service-terms cloud_data_processing_addendum: https://cloud.google.com/terms/data-processing-addendum privacy_notice: https://cloud.google.com/terms/cloud-privacy-notice ``` ## Eligibility ```yaml new_customer_only: true payment_method_required_for_verification: true ``` ## API compatibility and modalities - **Compatibility:** Provider-specific or not documented - **Modalities:** Model inference ## Before you build with Google Cloud Vertex AI ### 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. “One-time trial” should be interpreted together with the Current directory placement, High confidence, Yes payment-card status, and the plan-specific sources below. ### Resolve the live model route No stable model ID is recorded. Resolve the current machine-readable ID, endpoint, authentication method, and request shape from the provider's live documentation before writing fixed production configuration. ### 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 Yes, 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 **Partially private** because Google Cloud excludes training without permission, but caching, grounding, and session features introduce bounded retention. 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 12 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 - [Google Cloud free program](https://docs.cloud.google.com/free/docs/free-cloud-features): Official Trial - [Vertex generative AI pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing): Official Pricing - [OpenAI-compatible Gemini call on Vertex](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-gemini-chat-completions-non-streaming): Official Docs - [Google Cloud Terms](https://cloud.google.com/terms): Official Terms - [Google Cloud Service Specific Terms](https://cloud.google.com/terms/service-terms): Official Terms - [Google Cloud Data Processing Addendum](https://cloud.google.com/terms/data-processing-addendum): Official Dpa - [Google Cloud Privacy Notice](https://cloud.google.com/terms/cloud-privacy-notice): Official Privacy - [Vertex AI and zero data retention](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/vertex-ai-zero-data-retention): Official Docs - [Welcome to Google Cloud Next '26 (330 customers above one trillion tokens; 16B tokens/minute of direct API use), 2026-04-22](https://cloud.google.com/blog/topics/google-cloud-next/welcome-to-google-cloud-next26): Official Blog - [Welcome to Google Cloud Next '25 (40x growth in Gemini use on Vertex AI, billions of API calls per month), 2025-04-09](https://cloud.google.com/blog/topics/google-cloud-next/welcome-to-google-cloud-next25): Official Blog - [PyPI download stats for google-cloud-aiplatform (Vertex AI SDK)](https://pypistats.org/api/packages/google-cloud-aiplatform/recent): Package Registry Stats - [2025 Stack Overflow Developer Survey technology section](https://survey.stackoverflow.co/2025/technology): Independent Survey ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.