{ "data": { "similar": [ { "grade": "D", "json": "https://www.anchorterminal.com/tools/siliconflow.json", "name": "SiliconFlow", "score": 46.8, "shared": [ "inference.llm", "inference.open-weights", "embed.text", "image.generate", "video.generate", "speech.tts", "speech.stt" ], "slug": "siliconflow" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/cloudflare-workers-ai.json", "name": "Cloudflare Workers AI", "score": 69.2, "shared": [ "inference.llm", "inference.open-weights", "embed.text", "image.generate", "speech.stt", "speech.tts" ], "slug": "cloudflare-workers-ai" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/vercel-ai-gateway.json", "name": "Vercel AI Gateway", "score": 66.8, "shared": [ "inference.router", "inference.llm", "obs.gateway", "embed.text", "image.generate", "video.generate" ], "slug": "vercel-ai-gateway" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/deepinfra.json", "name": "DeepInfra", "score": 63.1, "shared": [ "inference.llm", "inference.open-weights", "embed.text", "image.generate", "speech.stt", "speech.tts" ], "slug": "deepinfra" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/localai.json", "name": "LocalAI", "score": 62.5, "shared": [ "inference.open-weights", "embed.text", "speech.stt", "speech.tts", "image.generate", "video.generate" ], "slug": "localai" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/koboldcpp.json", "name": "KoboldCpp", "score": 61, "shared": [ "inference.open-weights", "embed.text", "image.generate", "speech.stt", "speech.tts", "audio.music" ], "slug": "koboldcpp" } ], "tool": { "slug": "tencent-tokenhub", "name": "Tencent Cloud TokenHub", "vendor": "Tencent Cloud", "vendorUrl": "https://cloud.tencent.com", "kind": "router", "category": "inference", "summary": "Tencent Cloud TokenHub is a hosted model gateway serving Tencent's Hy models and third-party models such as DeepSeek, Kimi, GLM and MiniMax through OpenAI-compatible and Anthropic-compatible endpoints in Guangzhou and Singapore, with per-key scopes and quotas.", "url": "https://www.anchorterminal.com/tools/tencent-tokenhub", "markdownUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub.json", "dns": "tencent-tokenhub.grade.anchorterminal.com", "repo": "https://github.com/TencentCloud/THCLI", "license": "Proprietary service under the TokenHub Terms of Service, the TokenHub SLA and the Tencent Cloud Service Agreement, with a special note for third-party deployed models. The `tencent-tokenhub-cli` package is Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://tokenhub.tencentmaas.com/v1", "packages": [ { "registry": "npm", "name": "tencent-tokenhub-cli" } ], "auth": "api-key", "authNotes": "Bearer API key from the TokenHub console, or `x-api-key` on the Anthropic-style `/v1/messages`. Keys are long-lived, belong to one region (Guangzhou or Singapore), can be limited to chosen models and inference services, up to 200 IP ranges and token quotas, and can be disabled or deleted. They can also be created through the CreateApiKey control-plane call with signed Tencent Cloud credentials, or by `thcli auth login`. The account needs real-name verification first.", "pricing": "usage", "pricingNotes": "Pay per token in CNY, billed hourly. Hy4 preview costs 6 CNY in, 18 CNY out and 0.3 CNY cached per 1M tokens, Hy3 1, 4 and 0.25 CNY. DeepSeek models double at weekday peak hours. Batch is half price for Hy3 and Hy4 preview. Each account gets 1M free tokens per language model for a year, in a campaign to 31 December 2026. Token Plan subscriptions run from 28 to 599 CNY a month (https://cloud.tencent.com/document/product/1823/130055, checked 2026-11-01).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs table of contents, the billing pages or the API usage page. Payment is from a Tencent Cloud account balance, billed hourly (checked 2026-11-01).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 204, "pypiWeekly": null, "asOf": "2026-11-01" }, "docsUrl": "https://cloud.tencent.com/document/product/1823/130058", "rateLimitsUrl": "https://cloud.tencent.com/document/product/1823/136028", "llmsTxt": "https://cloud.tencent.com/document/product/1823/llms.txt", "capabilities": [ "inference.router", "inference.llm", "inference.open-weights", "embed.text", "embed.multimodal", "image.generate", "video.generate", "speech.tts", "speech.stt", "audio.music", "translate.text", "web.search", "obs.gateway" ], "tags": [ "hosted", "router", "usage-based", "free-credit", "openai-compatible", "anthropic-compatible", "llms-txt", "cli", "sla", "batch", "bug-bounty", "no-status-page", "regional-endpoints", "singapore", "chinese", "subscription" ], "lastRelease": "2026-10-24", "graded": true, "anchor": { "graded": true, "score": 59.5, "grade": "C", "agentReady": false, "rank": 646, "ranked": true, "rankOf": 1260, "categoryRank": 18, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 83, "maintenance": 73, "payments": 35, "reliability": 46, "schema": 73, "security": 71, "transparency": 54 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 46, "points": 9.2, "reason": "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).", "checked": "2026-11-01" }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 73, "points": 11.86, "reason": "Router, scored on the API lines. No OpenAPI file for the inference routes. Field pages document the OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats as TokenHub implements them, and the control plane is a Tencent Cloud API 3.0 service (version 2026-03-22) with typed parameters, API Explorer and SDKs (12 of 25). An llms.txt at cloud.tencent.com/document/product/1823/llms.txt links a Markdown copy of each docs page (10). The docs say which models support thinking, tools, structured output and caching, how TokenHub departs from each standard protocol, and which DeepSeek model suits which job. The quickstart's examples still use `deepseek-v3`, which is not in the model list, and Qwen3.5 stays in the list with a past shutdown date (13 of 20). Protocol pages list each field with type, required flag and default, and control-plane parameters carry enums and required flags (10 of 15). Examples in curl, Python, Node.js, Java and Go, and an error page listing 30 codes with HTTP status, cause and fix (14 of 15). Paths carry `/v1`, release notes are dated monthly from 7 April to 24 October 2026, and the control-plane API has a dated history of 26 releases to 18 September 2026 (14 of 15).", "checked": "2026-11-01" }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 83, "points": 13.49, "reason": "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).", "checked": "2026-11-01" }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 71, "points": 12.43, "reason": "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).", "checked": "2026-11-01" }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 35, "points": 4.38, "reason": "No x402, MPP or L402 (0). Per-token prices for every model are public in CNY for Guangzhou and Singapore, with DeepSeek's peak and off-peak rates (20). Each account gets 1M free tokens per language model, valid for a year, in a campaign running to 31 December 2026. No card is mentioned, but the account needs real-name verification, so this line takes 15 of 20. A person signs up and completes real-name verification in a browser. Keys can then be created in code or by `thcli auth login`, but only from that account (0).", "checked": "2026-11-01" }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 73, "points": 6.39, "reason": "Closed service, read on the model lines. The newest release note is dated 24 October 2026 and the price page was updated on 31 October (30). The four retirement notices read gave 21 to 33 days, and eligible callers are switched to a successor at its price. No minimum notice period is written, and DeepSeek-V4.1-Flash (directly supplied) was moved to the 1017 version under the same ids on 17 October 2026 in a notice dated two days later (7 of 12). 18 retirement notices from 21 April to 22 October 2026, 12 of them since 3 August (3 of 8). Dated release notes and announcements, ticket and phone support around the clock and a Q\u0026A community (13 of 15). Replies on the THCLI repository were not sampled (3 of 10). Tencent Cloud SDK 3.0 in several languages covers the control plane and `tencent-tokenhub-cli` 1.0.2 was published on 30 October 2026. No inference SDK of its own (12 of 15). The CLI has four releases since 15 September 2026, lists no runtime dependencies and needs Node.js 18 or later. CI not checked (5 of 10).", "checked": "2026-11-01" }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 54, "points": 4.72, "note": "editorial 59, provenance 49", "reason": "Closed service under the TokenHub Terms of Service (effective 14 September 2026), the SLA (23 April 2026), a special note on third-party deployed models and the Tencent Cloud Service Agreement, naming Tencent Cloud Computing (Beijing) Co., Ltd. The CLI is Apache-2.0 (18 of 30). The terms and the FAQ agree that inputs are processed on the customer's instructions and not used for training, and clause 2.14 limits retention to what the service needs without periods. The TokenHub privacy policy on privacy.qq.com renders only with JavaScript and was not read (15 of 30). Dated retirement notices, shutdown dates in the model list, a `pre-offline` status in `/v1/models` and a `DiscontinuedAt` field in the control API. Clause 6.3 refunds paid, unused tokens when a third-party model is removed. No minimum notice period is written (13 of 20). Clause 2.13 places processing generally in mainland China for the China site and in Singapore for the international site, and the third-party model list names DeepSeek's Hangzhou company with a link to its terms. No subprocessor list was found (13 of 20).", "checked": "2026-11-01" } ], "assessment": { "date": "2026-11-01", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "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).", "maintenance": "Closed service, read on the model lines. The newest release note is dated 24 October 2026 and the price page was updated on 31 October (30). The four retirement notices read gave 21 to 33 days, and eligible callers are switched to a successor at its price. No minimum notice period is written, and DeepSeek-V4.1-Flash (directly supplied) was moved to the 1017 version under the same ids on 17 October 2026 in a notice dated two days later (7 of 12). 18 retirement notices from 21 April to 22 October 2026, 12 of them since 3 August (3 of 8). Dated release notes and announcements, ticket and phone support around the clock and a Q\u0026A community (13 of 15). Replies on the THCLI repository were not sampled (3 of 10). Tencent Cloud SDK 3.0 in several languages covers the control plane and `tencent-tokenhub-cli` 1.0.2 was published on 30 October 2026. No inference SDK of its own (12 of 15). The CLI has four releases since 15 September 2026, lists no runtime dependencies and needs Node.js 18 or later. CI not checked (5 of 10).", "payments": "No x402, MPP or L402 (0). Per-token prices for every model are public in CNY for Guangzhou and Singapore, with DeepSeek's peak and off-peak rates (20). Each account gets 1M free tokens per language model, valid for a year, in a campaign running to 31 December 2026. No card is mentioned, but the account needs real-name verification, so this line takes 15 of 20. A person signs up and completes real-name verification in a browser. Keys can then be created in code or by `thcli auth login`, but only from that account (0).", "reliability": "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).", "schema": "Router, scored on the API lines. No OpenAPI file for the inference routes. Field pages document the OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats as TokenHub implements them, and the control plane is a Tencent Cloud API 3.0 service (version 2026-03-22) with typed parameters, API Explorer and SDKs (12 of 25). An llms.txt at cloud.tencent.com/document/product/1823/llms.txt links a Markdown copy of each docs page (10). The docs say which models support thinking, tools, structured output and caching, how TokenHub departs from each standard protocol, and which DeepSeek model suits which job. The quickstart's examples still use `deepseek-v3`, which is not in the model list, and Qwen3.5 stays in the list with a past shutdown date (13 of 20). Protocol pages list each field with type, required flag and default, and control-plane parameters carry enums and required flags (10 of 15). Examples in curl, Python, Node.js, Java and Go, and an error page listing 30 codes with HTTP status, cause and fix (14 of 15). Paths carry `/v1`, release notes are dated monthly from 7 April to 24 October 2026, and the control-plane API has a dated history of 26 releases to 18 September 2026 (14 of 15).", "security": "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).", "transparency": "Closed service under the TokenHub Terms of Service (effective 14 September 2026), the SLA (23 April 2026), a special note on third-party deployed models and the Tencent Cloud Service Agreement, naming Tencent Cloud Computing (Beijing) Co., Ltd. The CLI is Apache-2.0 (18 of 30). The terms and the FAQ agree that inputs are processed on the customer's instructions and not used for training, and clause 2.14 limits retention to what the service needs without periods. The TokenHub privacy policy on privacy.qq.com renders only with JavaScript and was not read (15 of 30). Dated retirement notices, shutdown dates in the model list, a `pre-offline` status in `/v1/models` and a `DiscontinuedAt` field in the control API. Clause 6.3 refunds paid, unused tokens when a third-party model is removed. No minimum notice period is written (13 of 20). Clause 2.13 places processing generally in mainland China for the China site and in Singapore for the international site, and the third-party model list names DeepSeek's Hangzhou company with a link to its terms. No subprocessor list was found (13 of 20)." }, "sources": [ { "what": "release notes", "url": "https://cloud.tencent.com/document/product/1823/130675", "seen": "2026-11-01" }, { "what": "product announcements", "url": "https://cloud.tencent.com/document/product/1823/130758", "seen": "2026-11-01" }, { "what": "product introduction", "url": "https://cloud.tencent.com/document/product/1823/130050", "seen": "2026-11-01" }, { "what": "model list", "url": "https://cloud.tencent.com/document/product/1823/130051", "seen": "2026-11-01" }, { "what": "model prices", "url": "https://cloud.tencent.com/document/product/1823/130055", "seen": "2026-11-01" }, { "what": "billing method", "url": "https://cloud.tencent.com/document/product/1823/130054", "seen": "2026-11-01" }, { "what": "free allowance", "url": "https://cloud.tencent.com/document/product/1823/130053", "seen": "2026-11-01" }, { "what": "arrears rules", "url": "https://cloud.tencent.com/document/product/1823/130056", "seen": "2026-11-01" }, { "what": "quickstart", "url": "https://cloud.tencent.com/document/product/1823/130058", "seen": "2026-11-01" }, { "what": "API usage and endpoints", "url": "https://cloud.tencent.com/document/product/1823/130078", "seen": "2026-11-01" }, { "what": "language model call overview", "url": "https://cloud.tencent.com/document/product/1823/130079", "seen": "2026-11-01" }, { "what": "API error codes", "url": "https://cloud.tencent.com/document/product/1823/131595", "seen": "2026-11-01" }, { "what": "OpenAI Chat Completions field reference", "url": "https://cloud.tencent.com/document/product/1823/135872", "seen": "2026-11-01" }, { "what": "batch inference", "url": "https://cloud.tencent.com/document/product/1823/130849", "seen": "2026-11-01" }, { "what": "prompt cache guide", "url": "https://cloud.tencent.com/document/product/1823/131410", "seen": "2026-11-01" }, { "what": "API key management", "url": "https://cloud.tencent.com/document/product/1823/130090", "seen": "2026-11-01" }, { "what": "quota management", "url": "https://cloud.tencent.com/document/product/1823/136028", "seen": "2026-11-01" }, { "what": "inference modes", "url": "https://cloud.tencent.com/document/product/1823/135900", "seen": "2026-11-01" }, { "what": "TPM reservation", "url": "https://cloud.tencent.com/document/product/1823/135901", "seen": "2026-11-01" }, { "what": "audit and call logs", "url": "https://cloud.tencent.com/document/product/1823/133523", "seen": "2026-11-01" }, { "what": "security governance", "url": "https://cloud.tencent.com/document/product/1823/138476", "seen": "2026-11-01" }, { "what": "content security protection", "url": "https://cloud.tencent.com/document/product/1823/134506", "seen": "2026-11-01" }, { "what": "network configuration", "url": "https://cloud.tencent.com/document/product/1823/131701", "seen": "2026-11-01" }, { "what": "model monitoring", "url": "https://cloud.tencent.com/document/product/1823/130089", "seen": "2026-11-01" }, { "what": "TokenHub CLI guide", "url": "https://cloud.tencent.com/document/product/1823/138217", "seen": "2026-11-01" }, { "what": "control-plane API update history", "url": "https://cloud.tencent.com/document/product/1823/132290", "seen": "2026-11-01" }, { "what": "CreateApiKey", "url": "https://cloud.tencent.com/document/product/1823/133810", "seen": "2026-11-01" }, { "what": "FAQ", "url": "https://cloud.tencent.com/document/product/1823/130104", "seen": "2026-11-01" }, { "what": "contact", "url": "https://cloud.tencent.com/document/product/1823/130109", "seen": "2026-11-01" }, { "what": "Token Plan for individuals", "url": "https://cloud.tencent.com/document/product/1823/130060", "seen": "2026-11-01" }, { "what": "Claude Code guide", "url": "https://cloud.tencent.com/document/product/1823/131903", "seen": "2026-11-01" }, { "what": "TokenHub SLA", "url": "https://cloud.tencent.com/document/product/301/129851", "seen": "2026-11-01" }, { "what": "TokenHub Terms of Service", "url": "https://cloud.tencent.com/document/product/301/129852", "seen": "2026-11-01" }, { "what": "special note on third-party deployed models", "url": "https://cloud.tencent.com/document/product/301/136530", "seen": "2026-11-01" }, { "what": "DeepSeek outage compensation notice, 15 October 2026", "url": "https://cloud.tencent.com/announce/detail/2517", "seen": "2026-11-01" }, { "what": "DeepSeek-V4.1-Flash version switch notice", "url": "https://cloud.tencent.com/announce/detail/2516", "seen": "2026-11-01" }, { "what": "MiniMax-M2.7 retirement notice", "url": "https://cloud.tencent.com/announce/detail/2511", "seen": "2026-11-01" }, { "what": "DeepSeek-V4-Flash 0731 retirement notice", "url": "https://cloud.tencent.com/announce/detail/2496", "seen": "2026-11-01" }, { "what": "Hy-Image-3.0 and Seedream lite retirement notice", "url": "https://cloud.tencent.com/announce/detail/2524", "seen": "2026-11-01" }, { "what": "GLM-5 family retirement notice", "url": "https://cloud.tencent.com/announce/detail/2469", "seen": "2026-11-01" }, { "what": "old platform shutdown notice", "url": "https://cloud.tencent.com/announce/detail/2287", "seen": "2026-11-01" }, { "what": "terms and SLA update notice", "url": "https://cloud.tencent.com/announce/detail/2262", "seen": "2026-11-01" }, { "what": "DeepSeek web search charge notice", "url": "https://cloud.tencent.com/announce/detail/2538", "seen": "2026-11-01" }, { "what": "product page", "url": "https://cloud.tencent.com/product/tokenhub", "seen": "2026-11-01" }, { "what": "docs llms.txt", "url": "https://cloud.tencent.com/document/product/1823/llms.txt", "seen": "2026-11-01" }, { "what": "npm registry, tencent-tokenhub-cli", "url": "https://registry.npmjs.org/tencent-tokenhub-cli", "seen": "2026-11-01" }, { "what": "THCLI README", "url": "https://raw.githubusercontent.com/TencentCloud/THCLI/main/README.md", "seen": "2026-11-01" }, { "what": "Tencent bug bounty policy", "url": "https://en.security.tencent.com/policy", "seen": "2026-11-01" }, { "what": "RDAP, tencentmaas.com", "url": "https://rdap.verisign.com/com/v1/domain/tencentmaas.com", "seen": "2026-11-01" } ], "openQuestions": [ "unchecked: whether an account on the international site (www.tencentcloud.com) can use TokenHub, since that site answered with a bot check, and whether a non-Chinese person can complete real-name verification on cloud.tencent.com", "unchecked: the TokenHub privacy policy on privacy.qq.com, which renders only with JavaScript", "unchecked: a public status page or health dashboard for TokenHub. The Tencent Cloud health dashboard documentation answered with a bot check", "unchecked: certifications (ISO 27001, SOC 2, MLPS) covering TokenHub specifically", "unchecked: per-model RPM and TPM defaults for chat models, which are shown only in the console and the DescribeModelQuota API", "The switch of DeepSeek-V4.1-Flash (directly supplied) to the 1017 version on 17 October 2026, announced on 19 October under unchanged ids and prices, was not deducted. It changes model behaviour, not the API, as with SiliconFlow's routing of retired models to successors", "The lead called TokenHub a late-October launch. The release notes date it to 7 April 2026, so it is seven months old" ] }, "negative": -3, "negativeNotes": [ "2026-10-17. -3, a breaking change without notice. DeepSeek-V4.1-Flash (directly supplied) was moved to its 1017 version under the same model ids and prices on 17 October 2026, and the notice came two days later (https://cloud.tencent.com/announce/detail/2516). Callers pinned to the id got a different model's behaviour with no warning. One term at the floor: the API didn't change. The founder's decision, 1 November 2026." ], "verdict": "Keys can be limited to chosen models, source IPs and token quotas, errors name their source and code, and a 99.5% SLA covers paid use of models Tencent runs. Sign-up needs a Tencent Cloud account with real-name verification, prices are in CNY, no public status page was found, and 18 model retirement notices ran from April to October 2026.", "bestFor": "Teams in or near Tencent Cloud that want one key and bill for Tencent's Hy models and Chinese open-weight models (DeepSeek, Kimi, GLM, MiniMax, Qwen, MiMo) with per-key limits and CNY billing.", "strengths": [ "API keys can be limited to chosen models and inference services, up to 200 source IP ranges, and daily, monthly or total token quotas", "One base URL answers OpenAI Chat Completions, OpenAI Responses and Anthropic Messages calls, and `GET /v1/models` marks models due to retire as `pre-offline`", "Error bodies carry a six-digit code, English and Chinese messages, the source (client, gateway or upstream) and a request ID, and 429s can carry `Retry-After`", "A published SLA promises 99.5% monthly availability with voucher credits of 10 to 50 per cent of the month's fee, for paid use of models Tencent runs", "Per-call audit logs (request ID, key, client IP, status, tokens, latency) can be delivered to the customer's own Tencent Cloud CLS log service" ], "weaknesses": [ "Sign-up needs a Tencent Cloud account with real-name verification. The international site answered with a bot check, so access from outside China was not established", "No public status page was found. A four-hour outage of DeepSeek's directly supplied models on 15 October 2026 appears only as a compensation notice", "18 model retirement notices from 21 April to 22 October 2026. Those read gave 21 to 33 days, and eligible callers are switched to a successor at its price", "DeepSeek's directly supplied models send inputs to DeepSeek under its own terms, and the TokenHub SLA does not cover them", "Per-model RPM and TPM limits for chat models are shown in the console and the quota API, not in the public docs" ], "agentNotes": [ "Use `https://tokenhub.tencentmaas.com/v1` with keys made for Guangzhou and `https://tokenhub-intl.tencentmaas.com/v1` with keys made for Singapore. Keys do not work across the two", "Send the key as `Authorization: Bearer` on the OpenAI paths and as `x-api-key` on `/v1/messages`", "Parse `error.code` as a string or a number, since 429 codes can come back as integers, and wait for `Retry-After` before retrying", "Take model ids from `GET /v1/models` and watch for `pre-offline`. The quickstart's `deepseek-v3` example is not in the current model list", "Expect DeepSeek prices to double on weekdays from 9am to noon and 2pm to 6pm Beijing time, when the peak rate applies" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.5 } ], "editorialScores": { "ergonomics": 83, "maintenance": 73, "payments": 35, "reliability": 46, "schema": 73, "security": 71, "transparency": 59 }, "provenanceScore": 49, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-11-01", "grade": "C", "kind": "listed", "method": "0.7", "score": 59.5 } ] }, "connect": { "install": "npm i -g tencent-tokenhub-cli", "http": "curl https://tokenhub.tencentmaas.com/v1/models \\\n -H \"Authorization: Bearer $TOKENHUB_API_KEY\"", "claudeCode": "{\n \"env\": {\n \"ANTHROPIC_BASE_URL\": \"https://tokenhub.tencentmaas.com\",\n \"ANTHROPIC_AUTH_TOKEN\": \"YOUR_API_KEY\",\n \"ANTHROPIC_MODEL\": \"hy3\"\n }\n}" }, "letme": { "capability": "https://letme.dev/inference.router", "tool": "https://letme.dev/tencent-tokenhub" }, "notable": [ "The release notes date the launch to 7 April 2026, \"大模型服务平台 TokenHub 全新上线\", and record model additions through 24 October 2026 (https://cloud.tencent.com/document/product/1823/130675)", "TokenHub replaced Tencent Cloud's older model platforms (Hunyuan, the DeepSeek API of the knowledge engine). Sales stopped on 30 June 2026 and the old consoles and APIs shut on 30 September 2026 (https://cloud.tencent.com/announce/detail/2287)", "DeepSeek's directly supplied models were unavailable from 9:06 to 13:04 Beijing time on 15 October 2026 after a fault at DeepSeek. Affected accounts got vouchers equal to their spend on those models from 8 to 14 October (https://cloud.tencent.com/announce/detail/2517)", "DeepSeek-V4.1-Flash (directly supplied) was switched to the DeepSeek-V4.1-Flash-1017 version at 10:00 Beijing time on 17 October 2026 under the same model ids, in a notice dated 19 October (https://cloud.tencent.com/announce/detail/2516)", "Search and Fetch calls made by the built-in web search of DeepSeek's directly supplied models are charged from 1 November 2026, at 5 CNY per 1,000 successful requests each, in a notice dated 28 October (https://cloud.tencent.com/announce/detail/2538)", "The SLA promises 99.5% monthly availability, with vouchers of 10, 25 or 50 per cent of the month's fee below 99.5%, 99% and 95%. It excludes free use, and the third-party model note says it does not apply to third-party deployed models (https://cloud.tencent.com/document/product/301/129851)", "Clause 2.17 of the terms says inputs are not used to develop, train, fine-tune or improve Tencent Cloud's own models, and that third-party deployed models follow the third party's terms (https://cloud.tencent.com/document/product/301/129852)", "Clause 2.4 of the terms lists using robot, spider or crawler software as unfair use, and clause 4.9 forbids using inputs, outputs or model behaviour to evaluate competing models without written consent (https://cloud.tencent.com/document/product/301/129852)", "The third-party deployed model list names four DeepSeek models supplied directly by 杭州深度求索人工智能基础技术研究有限公司, with \"TokenHub SLA 不适用\" (https://cloud.tencent.com/document/product/301/136530)", "The CLI guide gives a prompt for an AI agent to install `thcli` from a script on a Tencent COS bucket. The skills it injects into an agent cover read-only commands only (https://cloud.tencent.com/document/product/1823/138217)", "tencentmaas.com was registered on 13 March 2026 and has no registrant in RDAP. Tencent Cloud's own docs name it as the API host (https://cloud.tencent.com/document/product/1823/130078)" ], "area": "models", "details": [ { "label": "Endpoints", "value": "Guangzhou https://tokenhub.tencentmaas.com (mainland China resources) and Singapore https://tokenhub-intl.tencentmaas.com (global), with backup hosts on tencentmaas.cn. Paths `/v1/chat/completions`, `/v1/responses`, `/v1/messages` and `/v1/models`. Calls across regions or sites are not supported" }, { "label": "Models on 1 November 2026", "value": "The API usage page lists Hy4 preview, Hy3, Hy-MT2 translation and Hy-Role models from Tencent, DeepSeek V4 and V4.1 (some supplied directly by DeepSeek), GLM-5.2 and 5.3, Kimi K2.6 to K3.1 Pro, MiniMax M2.7 to M3.1, Qwen3.5, MiMo and Step 5 Preview, plus image, video, 3D, speech, music, vision and embedding models" }, { "label": "Prices", "value": "CNY per 1M tokens, the same in Guangzhou and Singapore for most models. Hy4 preview 6 in, 18 out, 0.3 cached. Hy3 1, 4, 0.25. DeepSeek-V4.1-Flash 1, 4, 0.02 off-peak and 2, 8, 0.04 at weekday peak. Kimi K3.1 Pro 13, 68, 1.3. GLM-5.3 8, 28, 2 in Guangzhou. TokenHub web search 7 or 12 CNY per 1,000 calls" }, { "label": "Free allowance", "value": "One free pack per account, 1M tokens per language and multimodal model and credits for some video and 3D models, valid one year from claiming. The campaign runs to 31 December 2026. Calls stop when it runs out unless pay-as-you-go is switched on" }, { "label": "Subscriptions", "value": "Token Plan for individuals (Hy Token Plan from 28 to 468 CNY a month, the general plan from 39 to 599 CNY), Token Plan for enterprises, Coding Plan, reserved TPM and dedicated model units through a sales manager" }, { "label": "Rate limits", "value": "Per model and per account, shown in the console and returned by DescribeModelQuota. Increases are self-serve when weekly peak use is above 60%, at most twice a week. Batch jobs 20 created a minute and 10 active per account. Image models 5 concurrent" }, { "label": "Errors", "value": "JSON `error` with `code` (six digits), `message`, `message_zh`, `type`, `source` (client, gateway or upstream), `upstream_code`, `upstream_status` and `request_id`. 30 codes documented, including 402 for an exhausted free pack, 451 for filtered content and six 429 codes. Stream errors arrive as SSE error frames" }, { "label": "Credentials", "value": "Long-lived API keys, 50 per account by default. Scope to all or chosen models and inference services, IP allowlist of up to 200 ranges, daily, monthly or total token quota, enable, disable and delete. Control-plane calls (CreateApiKey and others) use Tencent Cloud API 3.0 signatures" }, { "label": "Batch", "value": "Hy3 and Hy4 preview at half the online price. JSONL in the customer's own COS bucket, one model per file, completion window set in hours, results written back to COS" }, { "label": "Data use in the terms", "value": "Clause 2.17 says inputs are not used to train Tencent Cloud's own models. Clause 2.13 places processing generally in mainland China for the China site and in Singapore for the international site. Clause 2.14 keeps data only as long as the service needs, with no periods stated" }, { "label": "Logs and monitoring", "value": "Audit logs and full call logs can be delivered to the customer's CLS (billed separately). The console shows usage by key, model and service, and TTFT, TPOT, error and 429 rates" }, { "label": "Optional security", "value": "LLM-WAF checks inputs and outputs for prompt injection, banned content and sensitive data, in Guangzhou only and billed separately. PrivateLink connections from a VPC keep calls off the public internet" }, { "label": "Contract", "value": "Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算（北京）有限责任公司) under the TokenHub Terms of Service (effective 14 September 2026) and SLA (effective 23 April 2026), supplementing the Tencent Cloud Service Agreement" }, { "label": "Support", "value": "Tickets and phone support around the clock, presales chat and the Tencent Cloud Q\u0026A community" } ], "deprecations": [ { "what": "Tencent Cloud's older model platforms (Hunyuan, the knowledge engine's DeepSeek API) shut, with users moved to TokenHub", "date": "2026-09-30", "source": "https://cloud.tencent.com/announce/detail/2287", "kind": "shutdown" }, { "what": "GLM-5, GLM-5-Turbo and GLM-5.1 retired, with callers switched to GLM-5.3 and GLM-5.1 batch inference ended without migration", "date": "2026-10-09", "source": "https://cloud.tencent.com/announce/detail/2469", "kind": "shutdown" }, { "what": "DeepSeek-V4.1-Flash (directly supplied) switched to the DeepSeek-V4.1-Flash-1017 version under the same ids, announced on 19 October", "date": "2026-10-17", "source": "https://cloud.tencent.com/announce/detail/2516", "kind": "notice" }, { "what": "DeepSeek-V4-Flash 0731 retired, with eligible callers switched to the newest DeepSeek model", "date": "2026-10-31", "source": "https://cloud.tencent.com/announce/detail/2496", "kind": "shutdown" }, { "what": "Web search Search and Fetch calls of DeepSeek's directly supplied models charged at 5 CNY per 1,000 successful requests", "date": "2026-11-01", "source": "https://cloud.tencent.com/announce/detail/2538", "kind": "price" }, { "what": "Hy-Image-3.0 retired, with Hy-Image-3.5-preview recommended", "date": "2026-11-12", "source": "https://cloud.tencent.com/announce/detail/2524", "kind": "shutdown" }, { "what": "MiniMax-M2.7 retired, with eligible callers switched to MiniMax-M3", "date": "2026-11-17", "source": "https://cloud.tencent.com/announce/detail/2511", "kind": "shutdown" }, { "what": "Seedream-Image-v5.0-lite retired, with Seedream-Image-v5.0-flash recommended", "date": "2026-11-24", "source": "https://cloud.tencent.com/announce/detail/2524", "kind": "shutdown" } ], "provenance": { "legalEntity": "Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算（北京）有限责任公司)", "domain": "tencentmaas.com", "domainRegistered": "2026-03-13", "endpointOnVendorDomain": false, "terms": "https://cloud.tencent.com/document/product/301/129852", "privacy": "https://privacy.qq.com/document/preview/91d5fd3c98ce4468ae462ac59233bba2", "statusPage": "", "changelog": "https://cloud.tencent.com/document/product/1823/130675", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The TokenHub Terms of Service (effective 14 September 2026), the SLA (effective 23 April 2026) and the special note on third-party deployed models (effective 14 September 2026) name 腾讯云计算（北京）有限责任公司. The docs footer also names 深圳市腾讯计算机系统有限公司 as ICP licence holder.", "The TokenHub privacy policy is linked from the docs to privacy.qq.com, which renders only with JavaScript, so it was not read. privacy.qq.com has no robots.txt (404).", "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.", "security.txt answered 404 on cloud.tencent.com, www.tencent.com and tokenhub.tencentmaas.com. Tencent's bug bounty policy at en.security.tencent.com lists Tencent Cloud in scope.", "RDAP at Verisign gives tencentmaas.com a registration date of 13 March 2026 with no registrant. The API answers at tokenhub.tencentmaas.com and tokenhub-intl.tencentmaas.com, named in Tencent Cloud's API usage page.", "cloud.tencent.com allows these docs in robots.txt. Its pages answered some requests with a JavaScript bot check, which was not passed. The pages were read when a later plain request returned them. www.tencentcloud.com answered robots.txt with a bot check, so the international site was not read." ], "score": 49, "checks": [ { "check": "Legal entity named", "value": "Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算（北京）有限责任公司)", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "tencentmaas.com, registered 2026-03-13 (under a year)", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "tokenhub.tencentmaas.com is not on tencentmaas.com", "points": 0, "max": 15, "state": "no" }, { "check": "Terms of service", "value": "published, but our reader couldn't read it", "points": 7, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "published, but our reader couldn't read it", "points": 7, "max": 10, "state": "part" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "People named", "value": "6 named with their role, none with a public profile", "points": 7, "max": 10, "state": "part" }, { "check": "Support route", "value": "help pages, a community", "points": 5, "max": 5, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "https://cloud.tencent.com/document/product/301/129852", "state": "unreadable", "reason": "the page has 0 words of text without a browser, so the document is drawn by script or sits elsewhere", "readAt": "2026-11-01", "points": 7, "max": 10 }, { "kind": "privacy", "url": "https://privacy.qq.com/document/preview/91d5fd3c98ce4468ae462ac59233bba2", "state": "unreadable", "reason": "the page has 0 words of text without a browser, so the document is drawn by script or sits elsewhere", "readAt": "2026-11-01", "points": 7, "max": 10 } ] }, "humans": { "slug": "tencent-tokenhub", "checked": "2026-11-01", "company": "Tencent Cloud", "people": [ { "name": "Ma Huateng (Pony Ma)", "role": "Co-founder, Chairman of the Board and Chief Executive Officer, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-ma-huateng-pony-ma.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "bio": "Ma Huateng (Pony Ma) co-founded Tencent in 1998 and is its chairman and chief executive, leading the group's strategy, direction and management. Before Tencent he led research and development for an internet paging system at China Motion Telecom Development.", "bioSources": [ "https://www.tencent.com/team/ma-huateng-pony-ma/" ], "page": "/people/ma-huateng-pony-ma/" }, { "name": "Xu Chenye (Daniel Xu)", "role": "Co-founder and Chief Information Officer, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-xu-chenye-daniel-xu.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "page": "/people/xu-chenye-daniel-xu/" }, { "name": "Zhang Zhidong (Tony Zhang)", "role": "Co-founder and Advisor Emeritus, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-zhang-zhidong-tony-zhang.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "page": "/people/zhang-zhidong-tony-zhang/" }, { "name": "Chen Yidan (Charles Chen)", "role": "Co-founder and Advisor Emeritus, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-chen-yidan-charles-chen.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "bio": "Chen Yidan, also known as Charles Chen, co-founded Tencent and was its chief administrative officer. He remains an Advisor Emeritus and is founder and honorary chairman of the Tencent Charity Foundation, and he also founded the Yidan Prize Foundation.", "bioSources": [ "https://www.tencent.com/who-we-are/our-team/", "https://en.wikipedia.org/wiki/Chen_Yidan" ], "page": "/people/chen-yidan-charles-chen/" }, { "name": "Zeng Liqing (Jason Zeng)", "role": "Co-founder and Advisor Emeritus, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-zeng-liqing-jason-zeng.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "page": "/people/zeng-liqing-jason-zeng/" }, { "name": "Tong Taosang (Dowson Tong)", "role": "Senior Executive Vice President, Tencent, and President of Cloud and Smart Industries Group", "photo": "/assets/img/people/tencent-cloud-tong-taosang-dowson-tong.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "bio": "Dowson Tong is a senior executive vice president of Tencent and has led its Cloud and Smart Industries Group, which runs the cloud business and enterprise services, since October 2018. He earlier ran Tencent's Social Network Group, which covered QQ, and before joining Tencent worked on messaging systems at Sendmail and server development at Oracle.", "bioSources": [ "https://www.tencent.com/team/tong-taosang-dowson-tong/" ], "page": "/people/tong-taosang-dowson-tong/" } ], "peopleNote": "TokenHub's docs, terms and announcements name no product lead, read on 1 November 2026. The npm package tencent-tokenhub-cli lists one maintainer account with no name or role, so it isn't listed as a person. Company-level people are carried over from the TencentDB Agent Memory listing (data/humans/tencentdb-agent-memory.json, checked 30 October 2026), which read Tencent's management page for the five co-founders and Dowson Tong, president of the Cloud and Smart Industries Group that runs Tencent Cloud. The contracting entity in the TokenHub terms and SLA is Tencent Cloud Computing (Beijing) Co., Ltd. Ownership and investors are left out so land.py carries over the Tencent Cloud record (a subsidiary of Tencent Holdings Limited, checked 30 October 2026), as nothing new was looked for. LinkedIn, X, Crunchbase and PitchBook weren't read, by the rules.", "companySocial": { "linkedin": "https://www.linkedin.com/company/tencent-cloud", "x": "https://x.com/tencentcloud", "github": "https://github.com/TencentCloud" }, "support": { "urls": [ "https://cloud.tencent.com/document/product/1823/130109", "https://console.cloud.tencent.com/workorder/category", "https://cloud.tencent.com/act/event/Online_service" ], "community": [ { "label": "Tencent Cloud developer Q\u0026A", "url": "https://cloud.tencent.com/developer/ask", "kind": "forum" } ], "contactUrls": [ "https://cloud.tencent.com/document/product/1823/130109" ] }, "sources": [ "https://cloud.tencent.com/document/product/1823/130109", "https://cloud.tencent.com/document/product/301/129852", "https://cloud.tencent.com/document/product/301/129851", "https://registry.npmjs.org/tencent-tokenhub-cli" ], "ownership": { "status": "subsidiary", "parent": "Tencent Holdings Limited", "checked": "2026-10-29", "sources": [ "https://raw.githubusercontent.com/TencentCloud/Octop/main/README.md", "https://www.tencent.com/who-we-are/our-team/", "https://www.tencent.com/investors/" ] } }, "pageJsonUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub.json", "live": { "slug": "tencent-tokenhub", "probe": { "target": "https://tokenhub.tencentmaas.com/v1", "method": "get", "lastAt": "2026-11-02T00:26:49.414210718Z", "lastOk": true, "lastStatus": 404, "lastMs": 838, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 826, "p95ms24h": 1067, "samples24h": 23, "samples30d": 23, "days": [ { "date": "2026-11-01", "probes": 18, "ok": 18 }, { "date": "2026-11-02", "probes": 5, "ok": 5 } ] }, "updatedAt": "2026-11-02T00:26:49.414210718Z" } }, "verify": { "accepts": "a page on tencentmaas.com or cloud.tencent.com or one of their subdomains, or the README at the root of github.com/TencentCloud/THCLI", "badgeUrl": "https://www.anchorterminal.com/badges/tencent-tokenhub.svg", "body": { "slug": "tencent-tokenhub", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/tencent-tokenhub\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/tencent-tokenhub.svg\" alt=\"Tencent Cloud TokenHub on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![Tencent Cloud TokenHub on Anchor Terminal](https://www.anchorterminal.com/badges/tencent-tokenhub.svg)](https://www.anchorterminal.com/tools/tencent-tokenhub)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/tencent-tokenhub\"\u003eTencent Cloud TokenHub on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/tencent-tokenhub", "json": "https://www.anchorterminal.com/tools/tencent-tokenhub.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/tencent-tokenhub.md", "mcp": "https://www.anchorterminal.com/mcp", "pricing": "https://www.anchorterminal.com/tools/tencent-tokenhub#pricing", "reviews": "https://www.anchorterminal.com/tools/tencent-tokenhub#reviews", "slim": "https://www.anchorterminal.com/tools/tencent-tokenhub.min.md" }, "markdown": "## Overview\n\n**Grade C · 59.5/100 · rank #646 of 1260 · #18 in Model APIs \u0026 inference · not agent-ready · confidence medium**\n\n\n## Assessment\n\nKeys can be limited to chosen models, source IPs and token quotas, errors name their source and code, and a 99.5% SLA covers paid use of models Tencent runs. Sign-up needs a Tencent Cloud account with real-name verification, prices are in CNY, no public status page was found, and 18 model retirement notices ran from April to October 2026.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Tencent Cloud (https://cloud.tencent.com) |\n| Kind | Model router |\n| Category | Model APIs \u0026 inference (https://www.anchorterminal.com/categories/inference) |\n| Transport | HTTP |\n| Endpoint | `https://tokenhub.tencentmaas.com/v1` |\n| Auth | API key · Bearer API key from the TokenHub console, or `x-api-key` on the Anthropic-style `/v1/messages`. Keys are long-lived, belong to one region (Guangzhou or Singapore), can be limited to chosen models and inference services, up to 200 IP ranges and token quotas, and can be disabled or deleted. They can also be created through the CreateApiKey control-plane call with signed Tencent Cloud credentials, or by `thcli auth login`. The account needs real-name verification first. |\n| Pricing | Pay per use (Pay per use) · Pay per token in CNY, billed hourly. Hy4 preview costs 6 CNY in, 18 CNY out and 0.3 CNY cached per 1M tokens, Hy3 1, 4 and 0.25 CNY. DeepSeek models double at weekday peak hours. Batch is half price for Hy3 and Hy4 preview. Each account gets 1M free tokens per language model for a year, in a campaign to 31 December 2026. Token Plan subscriptions run from 28 to 599 CNY a month (https://cloud.tencent.com/document/product/1823/130055, checked 2026-11-01). |\n| x402 | No · No x402, MPP or L402 in the docs table of contents, the billing pages or the API usage page. Payment is from a Tencent Cloud account balance, billed hourly (checked 2026-11-01). |\n| Licence | Proprietary service under the TokenHub Terms of Service, the TokenHub SLA and the Tencent Cloud Service Agreement, with a special note for third-party deployed models. The `tencent-tokenhub-cli` package is Apache-2.0 |\n| Packages | npm: `tencent-tokenhub-cli` |\n| Source | https://github.com/TencentCloud/THCLI |\n| Docs | https://cloud.tencent.com/document/product/1823/130058 |\n| llms.txt | https://cloud.tencent.com/document/product/1823/llms.txt |\n| Last release | 2026-10-24 |\n| npm downloads / week | 204 |\n| Endpoints | Guangzhou https://tokenhub.tencentmaas.com (mainland China resources) and Singapore https://tokenhub-intl.tencentmaas.com (global), with backup hosts on tencentmaas.cn. Paths `/v1/chat/completions`, `/v1/responses`, `/v1/messages` and `/v1/models`. Calls across regions or sites are not supported |\n| Models on 1 November 2026 | The API usage page lists Hy4 preview, Hy3, Hy-MT2 translation and Hy-Role models from Tencent, DeepSeek V4 and V4.1 (some supplied directly by DeepSeek), GLM-5.2 and 5.3, Kimi K2.6 to K3.1 Pro, MiniMax M2.7 to M3.1, Qwen3.5, MiMo and Step 5 Preview, plus image, video, 3D, speech, music, vision and embedding models |\n| Prices | CNY per 1M tokens, the same in Guangzhou and Singapore for most models. Hy4 preview 6 in, 18 out, 0.3 cached. Hy3 1, 4, 0.25. DeepSeek-V4.1-Flash 1, 4, 0.02 off-peak and 2, 8, 0.04 at weekday peak. Kimi K3.1 Pro 13, 68, 1.3. GLM-5.3 8, 28, 2 in Guangzhou. TokenHub web search 7 or 12 CNY per 1,000 calls |\n| Free allowance | One free pack per account, 1M tokens per language and multimodal model and credits for some video and 3D models, valid one year from claiming. The campaign runs to 31 December 2026. Calls stop when it runs out unless pay-as-you-go is switched on |\n| Subscriptions | Token Plan for individuals (Hy Token Plan from 28 to 468 CNY a month, the general plan from 39 to 599 CNY), Token Plan for enterprises, Coding Plan, reserved TPM and dedicated model units through a sales manager |\n| Rate limits | Per model and per account, shown in the console and returned by DescribeModelQuota. Increases are self-serve when weekly peak use is above 60%, at most twice a week. Batch jobs 20 created a minute and 10 active per account. Image models 5 concurrent |\n| Errors | JSON `error` with `code` (six digits), `message`, `message_zh`, `type`, `source` (client, gateway or upstream), `upstream_code`, `upstream_status` and `request_id`. 30 codes documented, including 402 for an exhausted free pack, 451 for filtered content and six 429 codes. Stream errors arrive as SSE error frames |\n| Credentials | Long-lived API keys, 50 per account by default. Scope to all or chosen models and inference services, IP allowlist of up to 200 ranges, daily, monthly or total token quota, enable, disable and delete. Control-plane calls (CreateApiKey and others) use Tencent Cloud API 3.0 signatures |\n| Batch | Hy3 and Hy4 preview at half the online price. JSONL in the customer's own COS bucket, one model per file, completion window set in hours, results written back to COS |\n| Data use in the terms | Clause 2.17 says inputs are not used to train Tencent Cloud's own models. Clause 2.13 places processing generally in mainland China for the China site and in Singapore for the international site. Clause 2.14 keeps data only as long as the service needs, with no periods stated |\n| Logs and monitoring | Audit logs and full call logs can be delivered to the customer's CLS (billed separately). The console shows usage by key, model and service, and TTFT, TPOT, error and 429 rates |\n| Optional security | LLM-WAF checks inputs and outputs for prompt injection, banned content and sensitive data, in Guangzhou only and billed separately. PrivateLink connections from a VPC keep calls off the public internet |\n| Contract | Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算（北京）有限责任公司) under the TokenHub Terms of Service (effective 14 September 2026) and SLA (effective 23 April 2026), supplementing the Tencent Cloud Service Agreement |\n| Support | Tickets and phone support around the clock, presales chat and the Tencent Cloud Q\u0026A community |\n| Capabilities | inference.router, inference.llm, inference.open-weights, embed.text, embed.multimodal, image.generate, video.generate, speech.tts, speech.stt, audio.music, translate.text, web.search, obs.gateway |\n| Tags | hosted, router, usage-based, free-credit, openai-compatible, anthropic-compatible, llms-txt, cli, sla, batch, bug-bounty, no-status-page, regional-endpoints, singapore, chinese, subscription |\n| JSON | https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub.json |\n\n## Score breakdown (methodology v0.7, October 2026 research run)\n\nAssessed 2026-11-01 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 46 | 9.2 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 73 | 11.9 |\n| Agent ergonomics | 13% | 16.2 | 83 | 13.5 |\n| Security \u0026 auth | 14% | 17.5 | 71 | 12.4 |\n| Payments \u0026 pricing | 10% | 12.5 | 35 | 4.4 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 73 | 6.4 |\n| Transparency \u0026 trust (editorial 59, provenance 49) | 7% | 8.8 | 54 | 4.7 |\n| Negative events | up to −15 | up to −15 | 2026-10-17. -3, a breaking change without notice. DeepSeek-V4.1-Flash (directly supplied) was moved to its 1017 version under the same model ids and prices on 17 October 2026, and the notice came two days later (https://cloud.tencent.com/announce/detail/2516). Callers pinned to the id got a different model's behaviour with no warning. One term at the floor: the API didn't change. The founder's decision, 1 November 2026. | -3 |\n| **Total** | | | | **59.5 → C** |\n\n### Why each score\n\n- Reliability 46 (checked 2026-11-01): 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).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 73 (checked 2026-11-01): Router, scored on the API lines. No OpenAPI file for the inference routes. Field pages document the OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats as TokenHub implements them, and the control plane is a Tencent Cloud API 3.0 service (version 2026-03-22) with typed parameters, API Explorer and SDKs (12 of 25). An llms.txt at cloud.tencent.com/document/product/1823/llms.txt links a Markdown copy of each docs page (10). The docs say which models support thinking, tools, structured output and caching, how TokenHub departs from each standard protocol, and which DeepSeek model suits which job. The quickstart's examples still use `deepseek-v3`, which is not in the model list, and Qwen3.5 stays in the list with a past shutdown date (13 of 20). Protocol pages list each field with type, required flag and default, and control-plane parameters carry enums and required flags (10 of 15). Examples in curl, Python, Node.js, Java and Go, and an error page listing 30 codes with HTTP status, cause and fix (14 of 15). Paths carry `/v1`, release notes are dated monthly from 7 April to 24 October 2026, and the control-plane API has a dated history of 26 releases to 18 September 2026 (14 of 15).\n- Agent ergonomics 83 (checked 2026-11-01): 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).\n- Security \u0026 auth 71 (checked 2026-11-01): 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).\n- Payments \u0026 pricing 35 (checked 2026-11-01): No x402, MPP or L402 (0). Per-token prices for every model are public in CNY for Guangzhou and Singapore, with DeepSeek's peak and off-peak rates (20). Each account gets 1M free tokens per language model, valid for a year, in a campaign running to 31 December 2026. No card is mentioned, but the account needs real-name verification, so this line takes 15 of 20. A person signs up and completes real-name verification in a browser. Keys can then be created in code or by `thcli auth login`, but only from that account (0).\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 73 (checked 2026-11-01): Closed service, read on the model lines. The newest release note is dated 24 October 2026 and the price page was updated on 31 October (30). The four retirement notices read gave 21 to 33 days, and eligible callers are switched to a successor at its price. No minimum notice period is written, and DeepSeek-V4.1-Flash (directly supplied) was moved to the 1017 version under the same ids on 17 October 2026 in a notice dated two days later (7 of 12). 18 retirement notices from 21 April to 22 October 2026, 12 of them since 3 August (3 of 8). Dated release notes and announcements, ticket and phone support around the clock and a Q\u0026A community (13 of 15). Replies on the THCLI repository were not sampled (3 of 10). Tencent Cloud SDK 3.0 in several languages covers the control plane and `tencent-tokenhub-cli` 1.0.2 was published on 30 October 2026. No inference SDK of its own (12 of 15). The CLI has four releases since 15 September 2026, lists no runtime dependencies and needs Node.js 18 or later. CI not checked (5 of 10).\n- Transparency \u0026 trust 54 (checked 2026-11-01): Closed service under the TokenHub Terms of Service (effective 14 September 2026), the SLA (23 April 2026), a special note on third-party deployed models and the Tencent Cloud Service Agreement, naming Tencent Cloud Computing (Beijing) Co., Ltd. The CLI is Apache-2.0 (18 of 30). The terms and the FAQ agree that inputs are processed on the customer's instructions and not used for training, and clause 2.14 limits retention to what the service needs without periods. The TokenHub privacy policy on privacy.qq.com renders only with JavaScript and was not read (15 of 30). Dated retirement notices, shutdown dates in the model list, a `pre-offline` status in `/v1/models` and a `DiscontinuedAt` field in the control API. Clause 6.3 refunds paid, unused tokens when a third-party model is removed. No minimum notice period is written (13 of 20). Clause 2.13 places processing generally in mainland China for the China site and in Singapore for the international site, and the third-party model list names DeepSeek's Hangzhou company with a link to its terms. No subprocessor list was found (13 of 20).\n\nFix list, everything this grade says the listing lacks, the biggest gain first (22 items). What it covers is at https://www.anchorterminal.com/fixes/tencent-tokenhub.md (JSON https://www.anchorterminal.com/fixes/tencent-tokenhub.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{\"listing\": \"tencent-tokenhub\", \"plan\": \"read\"}`, free while the beta runs\n\n### What we couldn't check\n\n- unchecked: whether an account on the international site (www.tencentcloud.com) can use TokenHub, since that site answered with a bot check, and whether a non-Chinese person can complete real-name verification on cloud.tencent.com\n- unchecked: the TokenHub privacy policy on privacy.qq.com, which renders only with JavaScript\n- unchecked: a public status page or health dashboard for TokenHub. The Tencent Cloud health dashboard documentation answered with a bot check\n- unchecked: certifications (ISO 27001, SOC 2, MLPS) covering TokenHub specifically\n- unchecked: per-model RPM and TPM defaults for chat models, which are shown only in the console and the DescribeModelQuota API\n- The switch of DeepSeek-V4.1-Flash (directly supplied) to the 1017 version on 17 October 2026, announced on 19 October under unchanged ids and prices, was not deducted. It changes model behaviour, not the API, as with SiliconFlow's routing of retired models to successors\n- The lead called TokenHub a late-October launch. The release notes date it to 7 April 2026, so it is seven months old\n\n### Sources\n\n- release notes: \u003chttps://cloud.tencent.com/document/product/1823/130675\u003e (seen 2026-11-01)\n- product announcements: \u003chttps://cloud.tencent.com/document/product/1823/130758\u003e (seen 2026-11-01)\n- product introduction: \u003chttps://cloud.tencent.com/document/product/1823/130050\u003e (seen 2026-11-01)\n- model list: \u003chttps://cloud.tencent.com/document/product/1823/130051\u003e (seen 2026-11-01)\n- model prices: \u003chttps://cloud.tencent.com/document/product/1823/130055\u003e (seen 2026-11-01)\n- billing method: \u003chttps://cloud.tencent.com/document/product/1823/130054\u003e (seen 2026-11-01)\n- free allowance: \u003chttps://cloud.tencent.com/document/product/1823/130053\u003e (seen 2026-11-01)\n- arrears rules: \u003chttps://cloud.tencent.com/document/product/1823/130056\u003e (seen 2026-11-01)\n- quickstart: \u003chttps://cloud.tencent.com/document/product/1823/130058\u003e (seen 2026-11-01)\n- API usage and endpoints: \u003chttps://cloud.tencent.com/document/product/1823/130078\u003e (seen 2026-11-01)\n- language model call overview: \u003chttps://cloud.tencent.com/document/product/1823/130079\u003e (seen 2026-11-01)\n- API error codes: \u003chttps://cloud.tencent.com/document/product/1823/131595\u003e (seen 2026-11-01)\n- OpenAI Chat Completions field reference: \u003chttps://cloud.tencent.com/document/product/1823/135872\u003e (seen 2026-11-01)\n- batch inference: \u003chttps://cloud.tencent.com/document/product/1823/130849\u003e (seen 2026-11-01)\n- prompt cache guide: \u003chttps://cloud.tencent.com/document/product/1823/131410\u003e (seen 2026-11-01)\n- API key management: \u003chttps://cloud.tencent.com/document/product/1823/130090\u003e (seen 2026-11-01)\n- quota management: \u003chttps://cloud.tencent.com/document/product/1823/136028\u003e (seen 2026-11-01)\n- inference modes: \u003chttps://cloud.tencent.com/document/product/1823/135900\u003e (seen 2026-11-01)\n- TPM reservation: \u003chttps://cloud.tencent.com/document/product/1823/135901\u003e (seen 2026-11-01)\n- audit and call logs: \u003chttps://cloud.tencent.com/document/product/1823/133523\u003e (seen 2026-11-01)\n- security governance: \u003chttps://cloud.tencent.com/document/product/1823/138476\u003e (seen 2026-11-01)\n- content security protection: \u003chttps://cloud.tencent.com/document/product/1823/134506\u003e (seen 2026-11-01)\n- network configuration: \u003chttps://cloud.tencent.com/document/product/1823/131701\u003e (seen 2026-11-01)\n- model monitoring: \u003chttps://cloud.tencent.com/document/product/1823/130089\u003e (seen 2026-11-01)\n- TokenHub CLI guide: \u003chttps://cloud.tencent.com/document/product/1823/138217\u003e (seen 2026-11-01)\n- control-plane API update history: \u003chttps://cloud.tencent.com/document/product/1823/132290\u003e (seen 2026-11-01)\n- CreateApiKey: \u003chttps://cloud.tencent.com/document/product/1823/133810\u003e (seen 2026-11-01)\n- FAQ: \u003chttps://cloud.tencent.com/document/product/1823/130104\u003e (seen 2026-11-01)\n- contact: \u003chttps://cloud.tencent.com/document/product/1823/130109\u003e (seen 2026-11-01)\n- Token Plan for individuals: \u003chttps://cloud.tencent.com/document/product/1823/130060\u003e (seen 2026-11-01)\n- Claude Code guide: \u003chttps://cloud.tencent.com/document/product/1823/131903\u003e (seen 2026-11-01)\n- TokenHub SLA: \u003chttps://cloud.tencent.com/document/product/301/129851\u003e (seen 2026-11-01)\n- TokenHub Terms of Service: \u003chttps://cloud.tencent.com/document/product/301/129852\u003e (seen 2026-11-01)\n- special note on third-party deployed models: \u003chttps://cloud.tencent.com/document/product/301/136530\u003e (seen 2026-11-01)\n- DeepSeek outage compensation notice, 15 October 2026: \u003chttps://cloud.tencent.com/announce/detail/2517\u003e (seen 2026-11-01)\n- DeepSeek-V4.1-Flash version switch notice: \u003chttps://cloud.tencent.com/announce/detail/2516\u003e (seen 2026-11-01)\n- MiniMax-M2.7 retirement notice: \u003chttps://cloud.tencent.com/announce/detail/2511\u003e (seen 2026-11-01)\n- DeepSeek-V4-Flash 0731 retirement notice: \u003chttps://cloud.tencent.com/announce/detail/2496\u003e (seen 2026-11-01)\n- Hy-Image-3.0 and Seedream lite retirement notice: \u003chttps://cloud.tencent.com/announce/detail/2524\u003e (seen 2026-11-01)\n- GLM-5 family retirement notice: \u003chttps://cloud.tencent.com/announce/detail/2469\u003e (seen 2026-11-01)\n- old platform shutdown notice: \u003chttps://cloud.tencent.com/announce/detail/2287\u003e (seen 2026-11-01)\n- terms and SLA update notice: \u003chttps://cloud.tencent.com/announce/detail/2262\u003e (seen 2026-11-01)\n- DeepSeek web search charge notice: \u003chttps://cloud.tencent.com/announce/detail/2538\u003e (seen 2026-11-01)\n- product page: \u003chttps://cloud.tencent.com/product/tokenhub\u003e (seen 2026-11-01)\n- docs llms.txt: \u003chttps://cloud.tencent.com/document/product/1823/llms.txt\u003e (seen 2026-11-01)\n- npm registry, tencent-tokenhub-cli: \u003chttps://registry.npmjs.org/tencent-tokenhub-cli\u003e (seen 2026-11-01)\n- THCLI README: \u003chttps://raw.githubusercontent.com/TencentCloud/THCLI/main/README.md\u003e (seen 2026-11-01)\n- Tencent bug bounty policy: \u003chttps://en.security.tencent.com/policy\u003e (seen 2026-11-01)\n- RDAP, tencentmaas.com: \u003chttps://rdap.verisign.com/com/v1/domain/tencentmaas.com\u003e (seen 2026-11-01)\n\n## Score history\n\nEvery move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub/history.json\n\n- 2026-11-01: graded 59.5 C (methodology 0.7)\n\n## Who's behind it (provenance 49/100, checked 2026-11-01)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算（北京）有限责任公司) | 20/20 |\n| Domain age | tencentmaas.com, registered 2026-03-13 (under a year) | 0/15 |\n| Endpoint on the vendor's domain | tokenhub.tencentmaas.com is not on tencentmaas.com | 0/15 |\n| Terms of service | published, but our reader couldn't read it | 7/10 |\n| Privacy policy | published, but our reader couldn't read it | 7/10 |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n| People named | 6 named with their role, none with a public profile | 7/10 |\n| Support route | help pages, a community | 5/5 |\n\nThe TokenHub Terms of Service (effective 14 September 2026), the SLA (effective 23 April 2026) and the special note on third-party deployed models (effective 14 September 2026) name 腾讯云计算（北京）有限责任公司. The docs footer also names 深圳市腾讯计算机系统有限公司 as ICP licence holder.\n\nThe TokenHub privacy policy is linked from the docs to privacy.qq.com, which renders only with JavaScript, so it was not read. privacy.qq.com has no robots.txt (404).\n\nNo public status page was found. status.cloud.tencent.com did not answer, and the Tencent Cloud health dashboard documentation answered with a bot check.\n\nsecurity.txt answered 404 on cloud.tencent.com, www.tencent.com and tokenhub.tencentmaas.com. Tencent's bug bounty policy at en.security.tencent.com lists Tencent Cloud in scope.\n\nRDAP at Verisign gives tencentmaas.com a registration date of 13 March 2026 with no registrant. The API answers at tokenhub.tencentmaas.com and tokenhub-intl.tencentmaas.com, named in Tencent Cloud's API usage page.\n\ncloud.tencent.com allows these docs in robots.txt. Its pages answered some requests with a JavaScript bot check, which was not passed. The pages were read when a later plain request returned them. www.tencentcloud.com answered robots.txt with a bot check, so the international site was not read.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://cloud.tencent.com/document/product/301/129852), read 2026-11-01. Our reader couldn't read it (the page has 0 words of text without a browser, so the document is drawn by script or sits elsewhere).\n\n\n**Privacy policy** (https://privacy.qq.com/document/preview/91d5fd3c98ce4468ae462ac59233bba2), read 2026-11-01. Our reader couldn't read it (the page has 0 words of text without a browser, so the document is drawn by script or sits elsewhere).\n\n\n## Humans behind the project (researched 2026-11-01 from public pages, not part of the grade)\n\n### Key people\n\n- Ma Huateng (Pony Ma), Co-founder, Chairman of the Board and Chief Executive Officer, Tencent\n- Xu Chenye (Daniel Xu), Co-founder and Chief Information Officer, Tencent\n- Zhang Zhidong (Tony Zhang), Co-founder and Advisor Emeritus, Tencent\n- Chen Yidan (Charles Chen), Co-founder and Advisor Emeritus, Tencent\n- Zeng Liqing (Jason Zeng), Co-founder and Advisor Emeritus, Tencent\n- Tong Taosang (Dowson Tong), Senior Executive Vice President, Tencent, and President of Cloud and Smart Industries Group\n- Note: TokenHub's docs, terms and announcements name no product lead, read on 1 November 2026. The npm package tencent-tokenhub-cli lists one maintainer account with no name or role, so it isn't listed as a person. Company-level people are carried over from the TencentDB Agent Memory listing (data/humans/tencentdb-agent-memory.json, checked 30 October 2026), which read Tencent's management page for the five co-founders and Dowson Tong, president of the Cloud and Smart Industries Group that runs Tencent Cloud. The contracting entity in the TokenHub terms and SLA is Tencent Cloud Computing (Beijing) Co., Ltd. Ownership and investors are left out so land.py carries over the Tencent Cloud record (a subsidiary of Tencent Holdings Limited, checked 30 October 2026), as nothing new was looked for. LinkedIn, X, Crunchbase and PitchBook weren't read, by the rules.\n- Tencent Cloud: LinkedIn https://www.linkedin.com/company/tencent-cloud X https://x.com/tencentcloud GitHub https://github.com/TencentCloud\n\n### Ownership and investors\n\n- Ownership: Part of Tencent Holdings Limited\n\n### Getting support\n\n- Help: https://cloud.tencent.com/document/product/1823/130109\n- Help: https://console.cloud.tencent.com/workorder/category\n- Help: https://cloud.tencent.com/act/event/Online_service\n- Community (Tencent Cloud developer Q\u0026A): https://cloud.tencent.com/developer/ask\n- Sources: https://cloud.tencent.com/document/product/1823/130109, https://cloud.tencent.com/document/product/301/129852, https://cloud.tencent.com/document/product/301/129851, https://registry.npmjs.org/tencent-tokenhub-cli\n\n## Live (updated 2026-11-02 00:26 UTC)\n\n- Right now: up, HTTP 404, 838 ms, checked 2026-11-02 00:26 UTC (get on `https://tokenhub.tencentmaas.com/v1`)\n- Uptime 24h 100.0% (23 probes) · 30 days 100.0% (23 probes) · p50 826 ms · p95 1.1 s\n- Always current: https://www.anchorterminal.com/api/v1/live/tencent-tokenhub.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Dated changes\n\n- 2026-09-30 · Shutdown · Tencent Cloud's older model platforms (Hunyuan, the knowledge engine's DeepSeek API) shut, with users moved to TokenHub (source: \u003chttps://cloud.tencent.com/announce/detail/2287\u003e)\n- 2026-10-09 · Shutdown · GLM-5, GLM-5-Turbo and GLM-5.1 retired, with callers switched to GLM-5.3 and GLM-5.1 batch inference ended without migration (source: \u003chttps://cloud.tencent.com/announce/detail/2469\u003e)\n- 2026-10-17 · Notice · DeepSeek-V4.1-Flash (directly supplied) switched to the DeepSeek-V4.1-Flash-1017 version under the same ids, announced on 19 October (source: \u003chttps://cloud.tencent.com/announce/detail/2516\u003e)\n- 2026-10-31 · Shutdown · DeepSeek-V4-Flash 0731 retired, with eligible callers switched to the newest DeepSeek model (source: \u003chttps://cloud.tencent.com/announce/detail/2496\u003e)\n- 2026-11-01 · Price change · Web search Search and Fetch calls of DeepSeek's directly supplied models charged at 5 CNY per 1,000 successful requests (source: \u003chttps://cloud.tencent.com/announce/detail/2538\u003e)\n- 2026-11-12 · Shutdown · Hy-Image-3.0 retired, with Hy-Image-3.5-preview recommended (source: \u003chttps://cloud.tencent.com/announce/detail/2524\u003e)\n- 2026-11-17 · Shutdown · MiniMax-M2.7 retired, with eligible callers switched to MiniMax-M3 (source: \u003chttps://cloud.tencent.com/announce/detail/2511\u003e)\n- 2026-11-24 · Shutdown · Seedream-Image-v5.0-lite retired, with Seedream-Image-v5.0-flash recommended (source: \u003chttps://cloud.tencent.com/announce/detail/2524\u003e)\n\nAll listings, as a calendar: https://www.anchorterminal.com/sunsets.ics\n\n## Strengths\n\n- API keys can be limited to chosen models and inference services, up to 200 source IP ranges, and daily, monthly or total token quotas\n- One base URL answers OpenAI Chat Completions, OpenAI Responses and Anthropic Messages calls, and `GET /v1/models` marks models due to retire as `pre-offline`\n- Error bodies carry a six-digit code, English and Chinese messages, the source (client, gateway or upstream) and a request ID, and 429s can carry `Retry-After`\n- A published SLA promises 99.5% monthly availability with voucher credits of 10 to 50 per cent of the month's fee, for paid use of models Tencent runs\n- Per-call audit logs (request ID, key, client IP, status, tokens, latency) can be delivered to the customer's own Tencent Cloud CLS log service\n\n## Weaknesses\n\n- Sign-up needs a Tencent Cloud account with real-name verification. The international site answered with a bot check, so access from outside China was not established\n- No public status page was found. A four-hour outage of DeepSeek's directly supplied models on 15 October 2026 appears only as a compensation notice\n- 18 model retirement notices from 21 April to 22 October 2026. Those read gave 21 to 33 days, and eligible callers are switched to a successor at its price\n- DeepSeek's directly supplied models send inputs to DeepSeek under its own terms, and the TokenHub SLA does not cover them\n- Per-model RPM and TPM limits for chat models are shown in the console and the quota API, not in the public docs\n\n\n\n## Before you call it (notes for agents)\n\n1. Use `https://tokenhub.tencentmaas.com/v1` with keys made for Guangzhou and `https://tokenhub-intl.tencentmaas.com/v1` with keys made for Singapore. Keys do not work across the two\n2. Send the key as `Authorization: Bearer` on the OpenAI paths and as `x-api-key` on `/v1/messages`\n3. Parse `error.code` as a string or a number, since 429 codes can come back as integers, and wait for `Retry-After` before retrying\n4. Take model ids from `GET /v1/models` and watch for `pre-offline`. The quickstart's `deepseek-v3` example is not in the current model list\n5. Expect DeepSeek prices to double on weekdays from 9am to noon and 2pm to 6pm Beijing time, when the peak rate applies\n\n## Connect\n\nInstall:\n\n```bash\nnpm i -g tencent-tokenhub-cli\n```\n\nFirst request:\n\n```bash\ncurl https://tokenhub.tencentmaas.com/v1/models \\\n -H \"Authorization: Bearer $TOKENHUB_API_KEY\"\n```\n\nClaude Code:\n\n```bash\n{\n \"env\": {\n \"ANTHROPIC_BASE_URL\": \"https://tokenhub.tencentmaas.com\",\n \"ANTHROPIC_AUTH_TOKEN\": \"YOUR_API_KEY\",\n \"ANTHROPIC_MODEL\": \"hy3\"\n }\n}\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| SiliconFlow | D | 46.8 | 1036 | inference.llm, inference.open-weights, embed.text, image.generate, video.generate, speech.tts, speech.stt | no | https://www.anchorterminal.com/tools/siliconflow.md |\n| Cloudflare Workers AI | B | 69.2 | 204 | inference.llm, inference.open-weights, embed.text, image.generate, speech.stt, speech.tts | no | https://www.anchorterminal.com/tools/cloudflare-workers-ai.md |\n| Vercel AI Gateway | B | 66.8 | 262 | inference.router, inference.llm, obs.gateway, embed.text, image.generate, video.generate | no | https://www.anchorterminal.com/tools/vercel-ai-gateway.md |\n| DeepInfra | B | 63.1 | 464 | inference.llm, inference.open-weights, embed.text, image.generate, speech.stt, speech.tts | no | https://www.anchorterminal.com/tools/deepinfra.md |\n| LocalAI | B | 62.5 | 498 | inference.open-weights, embed.text, speech.stt, speech.tts, image.generate, video.generate | no | https://www.anchorterminal.com/tools/localai.md |\n| KoboldCpp | C | 61 | 570 | inference.open-weights, embed.text, image.generate, speech.stt, speech.tts, audio.music | no | https://www.anchorterminal.com/tools/koboldcpp.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- The release notes date the launch to 7 April 2026, \"大模型服务平台 TokenHub 全新上线\", and record model additions through 24 October 2026 (source: \u003chttps://cloud.tencent.com/document/product/1823/130675\u003e)\n- TokenHub replaced Tencent Cloud's older model platforms (Hunyuan, the DeepSeek API of the knowledge engine). Sales stopped on 30 June 2026 and the old consoles and APIs shut on 30 September 2026 (source: \u003chttps://cloud.tencent.com/announce/detail/2287\u003e)\n- DeepSeek's directly supplied models were unavailable from 9:06 to 13:04 Beijing time on 15 October 2026 after a fault at DeepSeek. Affected accounts got vouchers equal to their spend on those models from 8 to 14 October (source: \u003chttps://cloud.tencent.com/announce/detail/2517\u003e)\n- DeepSeek-V4.1-Flash (directly supplied) was switched to the DeepSeek-V4.1-Flash-1017 version at 10:00 Beijing time on 17 October 2026 under the same model ids, in a notice dated 19 October (source: \u003chttps://cloud.tencent.com/announce/detail/2516\u003e)\n- Search and Fetch calls made by the built-in web search of DeepSeek's directly supplied models are charged from 1 November 2026, at 5 CNY per 1,000 successful requests each, in a notice dated 28 October (source: \u003chttps://cloud.tencent.com/announce/detail/2538\u003e)\n- The SLA promises 99.5% monthly availability, with vouchers of 10, 25 or 50 per cent of the month's fee below 99.5%, 99% and 95%. It excludes free use, and the third-party model note says it does not apply to third-party deployed models (source: \u003chttps://cloud.tencent.com/document/product/301/129851\u003e)\n- Clause 2.17 of the terms says inputs are not used to develop, train, fine-tune or improve Tencent Cloud's own models, and that third-party deployed models follow the third party's terms (source: \u003chttps://cloud.tencent.com/document/product/301/129852\u003e)\n- Clause 2.4 of the terms lists using robot, spider or crawler software as unfair use, and clause 4.9 forbids using inputs, outputs or model behaviour to evaluate competing models without written consent (source: \u003chttps://cloud.tencent.com/document/product/301/129852\u003e)\n- The third-party deployed model list names four DeepSeek models supplied directly by 杭州深度求索人工智能基础技术研究有限公司, with \"TokenHub SLA 不适用\" (source: \u003chttps://cloud.tencent.com/document/product/301/136530\u003e)\n- The CLI guide gives a prompt for an AI agent to install `thcli` from a script on a Tencent COS bucket. The skills it injects into an agent cover read-only commands only (source: \u003chttps://cloud.tencent.com/document/product/1823/138217\u003e)\n- tencentmaas.com was registered on 13 March 2026 and has no registrant in RDAP. Tencent Cloud's own docs name it as the API host (source: \u003chttps://cloud.tencent.com/document/product/1823/130078\u003e)\n\n- #18 of 33 in Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 529 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Compare\n\n- [Claude API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub.md): BB 77.3 vs C 59.5\n- [BlockRun.AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/blockrun-ai-vs-tencent-tokenhub.md): A 78.9 vs C 59.5\n- [Cerebras Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cerebras-inference-vs-tencent-tokenhub.md): B 68.6 vs C 59.5\n- [Cloudflare AI Gateway vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-tencent-tokenhub.md): B 67.8 vs C 59.5\n- [Cloudflare Workers AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-tencent-tokenhub.md): B 69.2 vs C 59.5\n- [Cohere Chat API (Command models) vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub.md): B 64.7 vs C 59.5\n- [DeepInfra vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/deepinfra-vs-tencent-tokenhub.md): B 63.1 vs C 59.5\n- [DeepSeek API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/deepseek-api-vs-tencent-tokenhub.md): E 45.8 vs C 59.5\n- [Glimpse vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/elorian-glimpse-vs-tencent-tokenhub.md): D 48.8 vs C 59.5\n- [Fireworks AI Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/fireworks-inference-vs-tencent-tokenhub.md): B 69.3 vs C 59.5\n- [Gemini Developer API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/gemini-api-vs-tencent-tokenhub.md): B 65.5 vs C 59.5\n- [GroqCloud vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/groq-vs-tencent-tokenhub.md): BB 74.5 vs C 59.5\n- [Jais 3 vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub.md): D 52.1 vs C 59.5\n- [Meta Model API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.md): D 52.3 vs C 59.5\n- [MiniMax API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/minimax-api-vs-tencent-tokenhub.md): C 55.3 vs C 59.5\n- [Mistral AI API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/mistral-api-vs-tencent-tokenhub.md): B 65.7 vs C 59.5\n- [Muse Spark Open vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.md): D 53.4 vs C 59.5\n- [Novita AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub.md): D 53.5 vs C 59.5\n- [OpenAI API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/openai-api-vs-tencent-tokenhub.md): A 83.9 vs C 59.5\n- [OpenRouter vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/openrouter-vs-tencent-tokenhub.md): B 66.6 vs C 59.5\n- [Beam 1.0 vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/reflection-beam-vs-tencent-tokenhub.md): D 53.3 vs C 59.5\n- [SambaCloud vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/sambanova-vs-tencent-tokenhub.md): B 66.4 vs C 59.5\n- [SiliconFlow vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/siliconflow-vs-tencent-tokenhub.md): D 46.8 vs C 59.5\n- [Simplismart vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/simplismart-vs-tencent-tokenhub.md): F 29.5 vs C 59.5\n- [StepFun API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub.md): E 44.3 vs C 59.5\n- [Tencent Cloud TokenHub vs Together AI Inference](https://www.anchorterminal.com/compare/tencent-tokenhub-vs-together-inference.md): C 59.5 vs B 67.8\n- [Nemotron 3.5 Super VL vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub.md): C 58.8 vs C 59.5\n- [Prism Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/prism-inference-vs-tencent-tokenhub.md): C 60.3 vs C 59.5\n- [Antseed vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/antseed-vs-tencent-tokenhub.md): C 55.1 vs C 59.5\n- [Router.com (Ramp Router) vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub.md): C 54.3 vs C 59.5\n- [RouterPlus vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/routerplus-vs-tencent-tokenhub.md): D 51.4 vs C 59.5\n- [Tencent Cloud TokenHub vs Vercel AI Gateway](https://www.anchorterminal.com/compare/tencent-tokenhub-vs-vercel-ai-gateway.md): C 59.5 vs B 66.8\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on tencentmaas.com or cloud.tencent.com or one of their subdomains, or the README at the root of github.com/TencentCloud/THCLI. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"tencent-tokenhub\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/tencent-tokenhub\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/tencent-tokenhub.svg\" alt=\"Tencent Cloud TokenHub on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Tencent Cloud TokenHub on Anchor Terminal](https://www.anchorterminal.com/badges/tencent-tokenhub.svg)](https://www.anchorterminal.com/tools/tencent-tokenhub)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/tencent-tokenhub\"\u003eTencent Cloud TokenHub on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Tencent Cloud TokenHub is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/tencent-tokenhub-dark.png\n- Light: https://www.anchorterminal.com/assets/share/tencent-tokenhub-light.png\n- Create a video and download its frames: https://www.anchorterminal.com/assets/listing-video/index.html?listing=tencent-tokenhub\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-02", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Model APIs \u0026 inference", "url": "https://www.anchorterminal.com/categories/inference" }, { "name": "Tencent Cloud TokenHub", "url": "" } ], "description": "Tencent Cloud TokenHub is a hosted model gateway serving Tencent's Hy models and third-party models such as DeepSeek, Kimi, GLM and MiniMax through OpenAI-compatible and Anthropic-compatible endpoints in Guangzhou and Singapore, with per-key scopes and quotas.", "facts": [ "rank #646 of 1260", "API key auth", "0 desk reviews" ], "h1": "Tencent Cloud TokenHub", "image": "https://www.anchorterminal.com/assets/og/tools-tencent-tokenhub.png", "path": "/tools/tencent-tokenhub", "published": "2026-10-01", "section": "tools", "title": "Tencent Cloud TokenHub review: pricing, alternatives, grade C", "toc": null, "updated": "2026-11-02", "url": "https://www.anchorterminal.com/tools/tencent-tokenhub" }, "tokens": { "markdown": 11200, "slim": 2480 }, "version": 1 }