--- title: "OVHcloud AI Endpoints free inference" description: "7 model routes currently listed at zero price. See verified limits, model IDs, privacy terms, and primary sources for OVHcloud AI Endpoints." canonical_url: "https://freeinferencing.com/provider/ovhcloud_ai_endpoints/" md_url: "https://freeinferencing.com/provider/ovhcloud_ai_endpoints.md" last_updated: "2026-09-19" --- # OVHcloud AI Endpoints > 7 model routes currently listed at zero price. ## Classification - **Directory:** Current - **Free access:** Free model routes - **Status:** Restricted access - **Confidence:** High - **Payment card:** Yes - **Account:** Not documented - **Equivalent paid value:** At least $200.00 once - **API endpoint:** `https://oai.endpoints.kepler.ai.cloud.ovh.net/v1` ## Models mentioned - `Qwen3Guard-Gen-8B` - `Qwen3Guard-Gen-0.6B` - `stable-diffusion-xl-base-v10` - `nvr-tts-de-de` - `nvr-tts-en-us` - `nvr-tts-es-es` - `nvr-tts-it-it` ## Limits and terms ```yaml anonymous_requests_per_minute_per_ip_per_model: 2 authenticated_requests_per_minute_per_project_per_model: 400 ``` ## What happens to your prompts? **Partially private.** Endpoint-specific prompt retention and training commitments were not found. 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: partial plan_scope: OVHcloud AI Endpoints under OVHcloud general and service-specific cloud agreements. prompt_retention: No public endpoint-specific prompt retention duration was verified. response_retention: not_documented ordinary_logging: OVHcloud processes technical, security, billing, and account data; the reviewed catalog does not specify inference-content logging. model_training: No endpoint-specific statement authorizing or prohibiting training on prompts and outputs was found. product_improvement: General service telemetry may be used for operation and improvement; content scope is not documented. human_or_operator_access: not_documented subprocessors_and_routing: OVHcloud operates the endpoints in its cloud regions; catalog models may carry separate licenses. deletion_controls: General GDPR rights exist; no inference-content deletion control or TTL was found. caveat: European cloud/privacy commitments are not equivalent to a documented zero-retention or no-training promise for AI Endpoints. agreements: terms_of_service: https://www.ovhcloud.com/en/terms-and-conditions/ privacy_policy: https://www.ovhcloud.com/en/personal-data-protection/ ``` ## Eligibility No structured eligibility block was recorded. ## API compatibility and modalities - **Compatibility:** OpenAI Images, Model Specific Rest, Grpc Tts, OpenAI Style Guard - **Modalities:** Image / vision, Speech / audio, Safety ## Before you build with OVHcloud AI Endpoints ### 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. “Free model routes” 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 7 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 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 Endpoint-specific prompt retention and training commitments were not found. 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 9 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 - [AI Endpoints catalog](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/): Official Catalog - [SDXL endpoint and rate limits](https://www.ovhcloud.com/en-gb/public-cloud/ai-endpoints/catalog/stable-diffusion-xl/): Official Model Page - [Qwen Guard endpoint](https://www.ovhcloud.com/de/public-cloud/ai-endpoints/catalog/qwen-guard-gen-8b/): Official Model Page - [Public Cloud free trial](https://www.ovhcloud.com/en/public-cloud/free-trial/): Official Trial - [OVHcloud Terms and Conditions](https://www.ovhcloud.com/en/terms-and-conditions/): Official Terms - [OVHcloud personal data protection](https://www.ovhcloud.com/en/personal-data-protection/): Official Privacy - [OVHcloud GitHub organization followers](https://github.com/ovh): Code Hosting Stats - [2024 Stack Overflow Developer Survey technology section](https://survey.stackoverflow.co/2024/technology): Independent Survey - [OVHcloud about page citing 1.6M customers and Europe's leading cloud provider](https://www.ovhcloud.com/en/about-us/): Official About ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.