Tencent Cloud TokenHub
Try Tencent Cloud TokenHub on us. Starter credit covers your first requests, then one key reaches all 14 Tencent Cloud TokenHub models, with the privacy posture shown on every route.
Tencent Cloud TokenHubtencent
These privacy labels describe Tencent Cloud TokenHub, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | Tencent Cloud TokenHub |
|---|---|
| API operator country | Not verified Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://www.tencentcloud.com/products/tokenhub |
| Models | 14 public models |
| Credits routes | 14 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | TokenHub's Singapore API uses global resource scheduling, not a Singapore-only inference guarantee. Only canaried chat routes with matching regional USD prices are enabled. No verified contractual ZDR, confidential-compute, or upstream E2EE claim is tracked. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- Not verified
The Singapore TokenHub ingress uses global resource scheduling. Ingress location is not GPU residency. - Can locations change?
- Global scheduling; individual request location and country set are not verified.
- Provider region pinning
- Tencent documents separate Guangzhou and US sites, but this integration uses the Singapore/global site only.
- Pinning through TrustedRouter
- Not supported by the current TrustedRouter integration.
- Infrastructure declaration
- Global, dynamically scheduled inference; no fixed-country residency commitment.
- Evidence
- Public TokenHub API documentation. Reviewed .
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Models served by Tencent Cloud TokenHub.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash |
IQ 126#22 | 1,048,576 | $0.15825/1M | $0.01/1M | $0.633/1M |
moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code |
IQ 111#73 | 262,144 | $1.00225/1M | $0.20045/1M | $4.22/1M |
moonshotai/kimi-k2.7-code-highspeedmoonshotai/Kimi: K2.7-Code-Highspeed |
— | 262,144 | $2.0045/1M | $0.4009/1M | $8.44/1M |
moonshotai/kimi-k2.8-previewKimi K2.8 Preview |
— | 1,048,576 | $1.055/1M | $0.26375/1M | $4.22/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 127#21 | 1,048,576 | $3.165/1M | $0.3165/1M | $15.825/1M |
stepfun/step-5-previewStepFun: Step 5 Preview |
— | 1,048,576 | $1.055/1M | $0.05275/1M | $2.8485/1M |
tencent/hy3Tencent: Hy3 |
IQ 99#128 | 262,144 | $0.13926/1M | $0.034815/1M | $0.55704/1M |
tencent/hy4-previewTencent: Hy4 preview |
IQ 113#63 | 1,000,000 | $0.87987/1M | $0.04431/1M | $2.638555/1M |
xiaomi/mimo-v2.6-flashXiaomi: MiMo-V2.6-Flash |
IQ 122#37 | 1,050,000 | $0.1477/1M | $0.01/1M | $0.2954/1M |
xiaomi/mimo-v2.6-proXiaomi: MiMo-V2.6-Pro |
IQ 125#26 | 1,050,000 | $0.458925/1M | $0.01/1M | $0.91785/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 118#48 | 1,048,576 | $1.477/1M | $0.2743/1M | $4.642/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 124#28 | 1,048,576 | $1.477/1M | $0.2743/1M | $4.642/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 119#45 | 1,048,576 | $0.15825/1M | $0.03165/1M | $0.5275/1M |
z-ai/glm-5.3-flashxZ.ai: GLM 5.3 FlashX |
— | 1,048,576 | $0.39035/1M | $0.079125/1M | $1.31875/1M |
Questions
Does Tencent Cloud TokenHub have zero data retention?
TrustedRouter does not currently mark Tencent Cloud TokenHub as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Tencent Cloud TokenHub end-to-end encrypted?
TrustedRouter does not currently mark Tencent Cloud TokenHub as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Tencent Cloud TokenHub models are available through TrustedRouter?
This page currently lists 14 public Tencent Cloud TokenHub models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.