--- title: "Replicate free inference" description: "A finite allowance for new accounts; it does not recur." canonical_url: "https://freeinferencing.com/provider/replicate/" md_url: "https://freeinferencing.com/provider/replicate.md" last_updated: "2026-09-19" --- # Replicate > A finite allowance for new accounts; it does not recur. ## Classification - **Directory:** Current - **Free access:** One-time trial - **Status:** Current trial - **Confidence:** High - **Payment card:** No - **Account:** Required - **Equivalent paid value:** Not quantifiable - **API endpoint:** `https://api.replicate.com/v1` ## Models mentioned No stable model IDs were recorded in this snapshot. ## Limits and terms ```yaml coverage: Dynamic subset of models can be run free for a small unquantified allowance. recurrence: none_documented no_card_granted_credit_requests_per_second: 1 no_card_granted_credit_requests_per_minute: 6 caveat: Billing setup is required after the model-specific initial allowance is exhausted. ``` ## What happens to your prompts? **Partially private.** API data is deleted after one hour by default, but community models, resultant data, and web history introduce additional handling. 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: Replicate API, web predictions, marketplace models, custom deployments, and training; each model can also impose third-party terms. prompt_retention: API prediction inputs, outputs, files, and logs are removed after one hour by default. Web-interface prediction data is retained indefinitely until manually deleted. response_retention: Same API one-hour and web indefinite retention rules. Training artifacts, custom models, and customer-saved files have separate resource lifecycles. ordinary_logging: Prediction metadata survives removal of input and output data, and Replicate collects service-performance and resultant data for billing, operations, development, diagnostics, and improvement. model_training: Replicate's Customer Data license permits training customer-requested derivative models but does not expressly authorize training unrelated foundation models on ordinary inference content. Model authors or third-party offerings can add separate terms. product_improvement: Replicate may compile non-Customer-Data Resultant Data and use it to improve its services and products; the terms limit Customer Data use to service delivery, customer-requested derivative training, and resultant-data creation. human_or_operator_access: Content is stored during the stated prediction window and may be processed for delivery, support, security, and legal obligations; community model code receives the full input and must be trusted separately. subprocessors_and_routing: Replicate uses listed subprocessors and executes models supplied by Replicate or community authors. Secret fields are redacted after delivery, but a model author can still misuse a secret received by model code. deletion_controls: API content expires after one hour by default. Web predictions can be manually deleted, which removes their input and output data and files; users must manage training and model resources separately. caveat: API and web retention differ sharply, and running third-party model code creates a separate trust boundary. Do not assume a model author cannot inspect an input merely because Replicate later deletes it. agreements: terms_of_service: https://replicate.com/terms/ privacy_policy: https://replicate.com/privacy/ ``` ## Eligibility ```yaml account_required: true payment_method_required_initially: false ``` ## API compatibility and modalities - **Compatibility:** Replicate Native Rest - **Modalities:** Model inference ## Before you build with Replicate ### 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, No 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 No, 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 **Partially private** because API data is deleted after one hour by default, but community models, resultant data, and web history introduce additional handling. 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 11 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 - [Billing](https://replicate.com/docs/topics/billing): Official Docs - [Prepaid credit](https://replicate.com/docs/topics/billing/prepaid-credit): Official Docs - [Prediction rate limits](https://replicate.com/docs/topics/predictions/rate-limits): Official Docs - [Replicate Terms of Service](https://replicate.com/terms/): Official Terms - [Replicate Privacy Policy](https://replicate.com/privacy/): Official Privacy - [Prediction data retention](https://replicate.com/docs/topics/predictions/data-retention/): Official Docs - [Secret inputs and model-author trust](https://replicate.com/docs/topics/predictions/secrets): Official Docs - [Replicate subprocessors](https://replicate.com/docs/topics/site-policy/subprocessors): Official Docs - [Try-for-free collection (limited number of runs, count undisclosed)](https://replicate.com/collections/try-for-free): Official Catalog - [Replicate Series B post (2 million signups, 30,000 paying customers), 2023-12-05](https://replicate.com/blog/series-b): Official Blog - [npm download stats for the official replicate client](https://www.npmjs.com/package/replicate): Package Registry Stats ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.