Nemotron 3.5 Super VL vs Tencent Cloud TokenHub

Nemotron 3.5 Super VL 51

Model reading. nvapi- bearer keys sent in a header. NVIDIA's NGC docs say personal keys are limited to the services and role chosen at creation and take an expiry, and service keys can be scoped to actions (25 of 30). Inference only, with no write operation, but no zero-retention option for the hosted trial was found, and the model page asks callers not to send confidential or personal data (8 of 20). The model reads web pages, PDFs and images an agent passes it, and NVIDIA publishes safety, bias and privacy subcards, but no prompt-injection guidance or results were found (5 of 15). No per-call log for API callers was found, only rate limits shown in the account (3 of 15). NVIDIA PSIRT takes vulnerability reports, linked from the card. www.nvidia.com/.well-known/security.txt answered 403 and build.nvidia.com has none, and no certification for the API catalogue was found (10 of 20). 51.

Tencent Cloud TokenHub 71

Router, read on the model lines. Bearer keys can be limited to chosen models and inference services, up to 200 source IP ranges and daily, monthly or total token quotas, can be disabled or deleted, and can be created in code through CreateApiKey with signed Tencent Cloud credentials. Keys are long-lived with no expiry setting or built-in rotation (26 of 30). Clause 2.17 of the terms says inputs are not used to train Tencent Cloud's own models, and the FAQ says data is not used for training. Inputs to third-party deployed models (DeepSeek's directly supplied ones) go to DeepSeek under its terms (14 of 20). Clause 2.14 keeps data only as long as the service needs, with no periods stated. When a customer asks for generated content without AI labels, Tencent Cloud keeps logs of who received it for at least six months. No zero-retention option was found (7 of 15). Per-call audit logs (request ID, key, client IP, status, tokens, latency) and optional full call logs go to the customer's CLS, billed separately, with usage by key and a monitoring dashboard (14 of 15). No security.txt on cloud.tencent.com, www.tencent.com or tokenhub.tencentmaas.com (404). Tencent's bug bounty through TSRC lists Tencent Cloud in scope. No certification for TokenHub was checked (10 of 20).

Nemotron 3.5 Super VL 65

Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). OpenAI-format tools, tool_choice auto, none, required or a named function, and parallel calls on by default (20 of 20). response_format with json_schema and strict in the OpenAPI file. Not tested by us (12 of 15). The card describes prefix caching for self-hosted serving, but no caching on the hosted endpoint is documented (2 of 10). 1M tokens in the weights, but the hosted page lists 262K, and completions are capped at 131,072 tokens (12 of 15). No batch mode (0 of 10). Any OpenAI SDK works with the base URL, and NVIDIA maintains langchain-nvidia-ai-endpoints. Only messages is required, but reasoning defaults to on at high effort and the reference defaults stream to true (10 of 15). Errors carry a message, type and request id, with no 429 or rate-limit body documented (9 of 15). 65.

Tencent Cloud TokenHub 83

Router, read on the model lines. Function calling is marked on most chat models in the model list, with behaviour depending on the model routed (14 of 20). Structured output is marked per model and missing on the MiniMax and Qwen models, and an unsupported response_format returns code 400006 (12 of 15). Cache-hit prices are published per model, Kimi K3.1 Pro lists five-minute and one-hour cache writes, and a guide covers prompt_cache_key and the X-Session-ID header for instance affinity (14 of 15). Most listed chat models have contexts of one million tokens, a judgement call since a router has no default model (15). Batch at half price covers only Hy3 and Hy4 preview, reads and writes JSONL in the customer's own COS bucket and is documented for the Guangzhou endpoint (5 of 10). No TokenHub inference SDK. The OpenAI and Anthropic SDKs work with a changed base URL, and Tencent Cloud SDK 3.0 and the thcli CLI cover the control plane (8 of 10). Errors return a code, English and Chinese messages, the source, the upstream code and status and a request ID, and stream errors arrive as SSE error frames (15 of 15).

Nemotron 3.5 Super VL 58

Hosted reading, for NVIDIA's trial endpoint. status.ngc.nvidia.com is a Statuspage site with NVIDIA Build and Cloud Functions components and a readable history (20). In the 90 days to 17 October two incidents, both minor for an API caller. SMS verification for NVIDIA Build was unavailable in China from 23 to 29 September, which affects sign-up, and on 10 August new Cloud Functions deployments failed for about three hours while existing deployments kept running (20). build.nvidia.com gives limits of up to 40 requests a minute and 10,000 a day, and says they vary by model and with other users' traffic (12 of 15). The OpenAPI file documents a 202 pending result with an NVCF-REQID to poll, but no 429, Retry-After or backoff guidance, and NVIDIA's FAQ says to expect long waits under load (3 of 15). No SLA for the trial. NVIDIA's SLAs come with AI Enterprise for self-hosted software (0). The card says v1.0 GA, but the hosted page calls the model early access and NVIDIA calls the catalogue a trial for prototyping only (3 of 10). 58.

Tencent Cloud TokenHub 46

Hosted reading. No public status page was found. status.cloud.tencent.com did not answer and the Tencent Cloud health dashboard documentation answered with a bot check (0). With no page there is no incident record to read (5 of 30). The announcements carry one incident, DeepSeek's directly supplied models unavailable from 9:06 to 13:04 Beijing time on 15 October 2026 after a fault at DeepSeek, compensated with vouchers. Rate limits are per model, shown in the console and returned by DescribeModelQuota. The public docs give numbers only for batch jobs (20 created a minute, 10 active), image models (5 concurrent) and DeepSeek V4 Flash and Pro (2,500 and 500 concurrent), with the rules for self-serve increases (8 of 15). Six 429 codes separate RPM, TPM, TPD, concurrency and upstream capacity, 429s may carry Retry-After and the docs advise exponential backoff. No idempotency guidance, though inference calls are not writes (13 of 15). The TokenHub SLA promises 99.5% monthly availability with vouchers of 10, 25 or 50 per cent of the month's fee. It excludes free use and third-party deployed models such as DeepSeek's directly supplied ones (10). Generally available since 7 April 2026, with some models marked preview (10).