--- title: "Amazon Bedrock free inference" description: "$100 for new accounts; it does not recur. See verified limits, model IDs, privacy terms, and primary sources for Amazon Bedrock." canonical_url: "https://freeinferencing.com/provider/aws_bedrock/" md_url: "https://freeinferencing.com/provider/aws_bedrock.md" last_updated: "2026-09-19" --- # Amazon Bedrock > $100 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:** At least $100.00 once - **API endpoint:** `https://bedrock-mantle.{region}.api.aws/openai/v1` ## Models mentioned No stable model IDs were recorded in this snapshot. ## Limits and terms ```yaml signup_credit_usd: 100 additional_earnable_credit_usd: 100 free_plan_duration_months: 6 credit_expiry_months_from_account_creation: 12 recurrence: false ``` ## What happens to your prompts? **Partially private.** Bedrock is zero-retention and no-training by default, but named model routes have current abuse-review retention exceptions. 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: Amazon Bedrock model inference; model-specific abuse rules and customer-enabled stateful features can differ from the default. prompt_retention: Bedrock defaults to zero data retention and does not store model inputs or outputs. Current exceptions include up to 30-day retention for classifier-flagged OpenAI GPT-5.4/5.5/5.6 traffic and all Anthropic Claude Fable 5 traffic, plus legally required CSAM handling. response_retention: Same default and model-specific exceptions as inputs. Customer-created agents, knowledge bases, invocation logging, batch files, and other AWS storage persist under their configured lifecycles. ordinary_logging: Bedrock retains metering and operational metadata, and customers can deliberately enable model-invocation logging to CloudWatch or S3. Content is automatically screened for abuse. model_training: AWS says it does not use Bedrock inputs or outputs to train or improve base models and does not share them with third-party model providers for that purpose. product_improvement: Customer content is excluded from base-model improvement; aggregate service telemetry and customer-provided feedback are separately governed. human_or_operator_access: Bedrock uses a zero-operator-access model by default. Stored abuse exceptions can be reviewed only for the specified safety purpose; customer support or customer-configured logs create separate access paths. subprocessors_and_routing: AWS hosts access to Amazon and third-party foundation models without sharing prompts with the original model providers, but model licenses and use policies still apply. deletion_controls: Ordinary stateless payloads are not stored. Customers control CloudWatch, S3, agents, knowledge bases, batch inputs, and other feature state through AWS retention and deletion settings. caveat: Model-specific safety exceptions now prevent treating every Bedrock route as strict ZDR. Inspect the selected model and any enabled logging or stateful feature. agreements: customer_agreement: https://aws.amazon.com/agreement/ service_terms: https://aws.amazon.com/service-terms/ privacy_notice: https://aws.amazon.com/privacy/ data_processing_addendum: https://d1.awsstatic.com/legal/aws-gdpr/AWS_GDPR_DPA.pdf ``` ## Eligibility ```yaml new_aws_customer_only: true payment_method_required: true ``` ## API compatibility and modalities - **Compatibility:** OpenAI Responses, OpenAI Chat Completions, Anthropic Messages, Bedrock Converse, Bedrock Invoke - **Modalities:** Text generation ## Before you build with Amazon Bedrock ### 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 Bedrock is zero-retention and no-training by default, but named model routes have current abuse-review retention exceptions. 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 - [AWS Free Tier credits and six-month plan](https://aws.amazon.com/about-aws/whats-new/2025/07/aws-free-tier-credits-month-free-plan/): Official Announcement - [Free Tier FAQ](https://docs.aws.amazon.com/awsaccountbilling/latest/aboutv2/free-tier-FAQ.html): Official Docs - [Bedrock pricing](https://aws.amazon.com/bedrock/pricing/): Official Pricing - [OpenAI-compatible inference](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-chat-completions-mantle.html): Official Docs - [AWS Customer Agreement](https://aws.amazon.com/agreement/): Official Terms - [AWS Service Terms](https://aws.amazon.com/service-terms/): Official Terms - [AWS Privacy Notice](https://aws.amazon.com/privacy/): Official Privacy - [AWS GDPR Data Processing Addendum](https://d1.awsstatic.com/legal/aws-gdpr/AWS_GDPR_DPA.pdf): Official Dpa - [Amazon Bedrock abuse detection and data handling](https://docs.aws.amazon.com/bedrock/latest/userguide/abuse-detection.html): Official Docs - [Amazon Bedrock tens of thousands of customers and 4.7x customer growth (2024-12-04)](https://press.aboutamazon.com/2024/12/amazon-bedrock-empowers-customers-to-accelerate-generative-ai-adoption-with-more-than-100-new-models-and-powerful-new-capabilities-for-inference-and-working-with-data): Official Press Release - [npm download stats for @aws-sdk/client-bedrock-runtime](https://www.npmjs.com/package/@aws-sdk/client-bedrock-runtime): 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.