--- title: "IBM watsonx.ai Runtime free inference" description: "A recurring no-cost API allowance covering 4 cataloged models." canonical_url: "https://freeinferencing.com/provider/ibm_watsonx_ai_runtime/" md_url: "https://freeinferencing.com/provider/ibm_watsonx_ai_runtime.md" last_updated: "2026-09-19" --- # IBM watsonx.ai Runtime > A recurring no-cost API allowance covering 4 cataloged models. ## Classification - **Directory:** Current - **Free access:** Always-free quota - **Status:** Available now - **Confidence:** High - **Payment card:** Yes - **Account:** Required - **Equivalent paid value:** At least $15.11/mo - **API endpoint:** `https://{region}.ml.cloud.ibm.com/ml/v1` ## Models mentioned - `granite-4-h-small` - `granite-4-h-tiny` - `granite-4-h-micro` - `granite-3-1-8b-base` ## Limits and terms ```yaml foundation_tokens_per_month: 300000 requests_per_second: 2 capacity_unit_hours: 20 extraction_pages: 100 plan: Lite inactivity: A Lite service can be deleted after 30 days of inactivity. ``` ## What happens to your prompts? **Private.** IBM says unsaved API prompts and outputs are not accessed, logged, stored, trained on, or used for improvement without permission. 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: IBM watsonx.ai SaaS foundation-model inference; saved assets, prompt sessions, tuning data, and third-party models have additional state and terms. prompt_retention: IBM states it does not access, log, or store unsaved API prompts or outputs. Content deliberately saved as project assets is stored until the customer deletes it; temporary prompt-session assets can persist for 30 days. response_retention: Unsaved API outputs receive the same no-log and no-store treatment; saved results follow project and feature lifecycle controls. ordinary_logging: IBM retains account and service-usage metadata for operations, security, metering, support, and contractual obligations without treating unsaved prompt content as ordinary logs. model_training: IBM states customer prompts and outputs are not used to train foundation models or improve the service without permission. product_improvement: Unsaved prompts and outputs are excluded from service or model improvement; separately supplied feedback, tuning data, or expressly authorized data can be governed by their feature terms. human_or_operator_access: IBM says unsaved API prompts and outputs are not accessed. Saved assets and support cases can be accessed as needed under IBM Cloud security and contractual controls. subprocessors_and_routing: IBM Cloud subprocessors and, where selected, third-party model providers may process data under the service terms and DPA; model-specific terms can add restrictions. deletion_controls: Customers can delete saved project assets; prompt-session assets expire after 30 days. Contract termination and personal-data rights follow IBM Cloud terms and privacy procedures. caveat: The strongest no-store statement applies to unsaved API requests. Prompt Lab history, projects, files, deployments, tuning data, support material, and third-party models can create separately retained state. agreements: cloud_service_terms: https://www.ibm.com/support/customer/csol/terms/ privacy_statement: https://www.ibm.com/privacy data_processing_addendum: https://www.ibm.com/support/customer/csol/terms/?id=i126-7875 ``` ## Eligibility ```yaml account_required: true payment_method_required_for_new_accounts: true caveat: New IBM Cloud accounts require a card for identity verification even when using Lite services. ``` ## API compatibility and modalities - **Compatibility:** Ibm Watsonx Rest And Sdks - **Modalities:** Model inference ## Before you build with IBM watsonx.ai Runtime ### 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. “Always-free quota” 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 The snapshot records 4 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 Yes, and account access is required. 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 IBM says unsaved API prompts and outputs are not accessed, logged, stored, trained on, or used for improvement without permission. 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 - [watsonx.ai Runtime plans](https://www.ibm.com/docs/en/watsonx/saas?topic=cloud-watsonxai-runtime-plans): Official Docs - [watsonx.ai Runtime service](https://cloud.ibm.com/catalog/services/pm-20): Official Catalog - [List foundation models programmatically](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-prompt-notebook-list-models.html?context=wx): Official Docs - [IBM unveils watsonx](https://newsroom.ibm.com/2023-05-09-IBM-Unveils-the-Watsonx-Platform-to-Power-Next-Generation-Foundation-Models-for-Business): Announcement - [IBM Cloud Service terms](https://www.ibm.com/support/customer/csol/terms/): Official Terms - [IBM Privacy Statement](https://www.ibm.com/privacy): Official Privacy - [IBM Data Processing Addendum](https://www.ibm.com/support/customer/csol/terms/?id=i126-7875): Official Dpa - [Security of foundation models in watsonx.ai](https://www.ibm.com/docs/en/watsonx/saas?topic=watsonx-security-foundation-models): Official Docs - [IBM watsonx.ai pricing](https://www.ibm.com/products/watsonx-ai/pricing): Official Pricing - [PyPI download stats for ibm-watsonx-ai](https://pypistats.org/packages/ibm-watsonx-ai): Package Registry Stats - [2025 Stack Overflow Developer Survey technology section](https://survey.stackoverflow.co/2025/technology): Independent Survey - [IBM Granite first-party model family](https://www.ibm.com/granite): Official Product ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.