--- title: "Tencent Cloud TokenHub free inference" description: "A possible free offer exists, but a decisive term still needs verification." canonical_url: "https://freeinferencing.com/provider/tencent_tokenhub/" md_url: "https://freeinferencing.com/provider/tencent_tokenhub.md" last_updated: "2026-10-06" --- # Tencent Cloud TokenHub > A possible free offer exists, but a decisive term still needs verification. ## Classification - **Directory:** Watchlist - **Free access:** One-time trial - **Status:** Needs Verification - **Confidence:** Medium - **Payment card:** No - **Account:** Required - **Equivalent paid value:** Not quantifiable - **API endpoint:** `https://tokenhub.tencentmaas.com/v1` ## Models mentioned No stable model IDs were recorded in this snapshot. ## Limits and terms ```yaml language_model_trial_tokens: 1000000 campaign_end: 2026-12-31 validity: One year from claim for language models, per September 17 documentation. claim_frequency: Once per root account per model; not recurring. hold_release: Destroy model endpoints to release the hold; default endpoint removal requires support. exhaustion: Stops unless postpaid use is explicitly enabled. accounting_conflict: The same page says all models share the root-account allowance and each model has a once-only package; do not sum grants without account confirmation. ``` ## What happens to your prompts? **Partially private.** Privacy protections are incomplete, conditional, or not fully documented. 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: International TokenHub trial; model/upstream and deployment-region terms differ. prompt_retention: Up to 30 days by default for service/debugging; zero-retention only when enabled in supported regions. response_retention: Same default retention scope as prompts. ordinary_logging: Diagnostic, configuration, request and billing logs; longer statutory or billing retention can apply. model_training: No end-to-end trial-wide exclusion established; third-party model agreements can prevail. product_improvement: Service privacy module permits feature improvement from service diagnostics; content-use scope depends on route. human_or_operator_access: Service/debug access permitted; sensitive personal data is prohibited. subprocessors_and_routing: Tencent-hosted models or third-party APIs/resellers, including content-safety services. Region and route affect handling. deletion_controls: Regional zero-retention settings and general privacy requests; exact trial-account availability unverified. agreements: terms_of_service: https://www.tencentcloud.com/document/product/301/78869 privacy_policy: https://intl.cloud.tencent.com/zh/document/product/1300/78952 data_processing_addendum: https://intl.cloud.tencent.com/zh/document/product/1300/78953 ``` ## Eligibility ```yaml account_required: true real_name_verification_required: true account_balance_or_credit_hold_usd: 1 payment_method_required: Balance or credit line required; exact account funding conditions not verified. ``` ## API compatibility and modalities - **Compatibility:** OpenAI Compatible - **Modalities:** Model inference ## Before you build with Tencent Cloud TokenHub ### Read the classification narrowly This record describes the bounded offer supported by evidence on 2026-10-06; 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 Watchlist directory placement, Medium 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 Privacy protections are incomplete, conditional, or not fully documented. 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 6 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 - [TokenHub new-user package, updated September 17 2026](https://intl.cloud.tencent.com/zh/document/product/1300/80423): Official Pricing - [Hunyuan to TokenHub migration and new API endpoint](https://cloud.tencent.com/document/product/1823/131382): Official Docs - [TokenHub account and identity requirements](https://cloud.tencent.cn/document/product/1823/130058): Official Docs - [TokenHub Terms, effective August 24 2026](https://www.tencentcloud.com/document/product/301/78869): Official Terms - [TokenHub service privacy module](https://intl.cloud.tencent.com/zh/document/product/1300/78952): Official Privacy - [TokenHub data processing and security module](https://intl.cloud.tencent.com/zh/document/product/1300/78953): Official Dpa ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.