Head to head · LLM inference · October 2026 research run
Tencent Hy4 vs Tencent Cloud TokenHub
Tencent Hy4 scores 64 (B) on agent readiness against Tencent Cloud TokenHub's 61.7 (C), and leads in 1 of 7 scored categories. Tencent Cloud TokenHub leads on payments & pricing. Both do llm inference.
Best model APIs and inference for AI agents · All 1044 models comparisons
Which one, for what
Best for Long-context agent work, coding and office or finance tasks on a 1M-token context with images, for teams already on Tencent Cloud or happy to verify an account there.
Also in its favour
- No incidents deducted, where Tencent Cloud TokenHub loses 3 points for them
Watch for
Weights, licence and system card are promised but not published; tencent/Hy4 didn't answer on Hugging Face on 11 November
Best for 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.
Ahead on
- Payments & pricing, 53 against 45
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
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
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Payments & pricing Tencent Cloud TokenHub +8
Tencent Hy4 45
Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No machine payment protocol (0). The price page, updated 9 November, lists ¥6 input, ¥0.3 cached and ¥18 output per million tokens, with Hy4 billed at 50% until 31 December 2026 (20). TokenHub's campaign of 1M free tokens per language model, read on 1 November, isn't confirmed for hy4 on the price page, so half (10 of 20, a judgement call). A person signs up with real-name verification (0). 0 + 20 + 10 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.
Tencent Cloud TokenHub 53
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). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 35 is 53.
Score by category
| Category | Weight this run | Tencent Hy4 | Tencent Cloud TokenHub | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 46 | 46 | even |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 73 | 73 | even |
| Agent ergonomics | 13%16.2 | 86 | 83 | Tencent Hy4 +3 |
| Security & auth | 14%17.5 | 71 | 71 | even |
| Payments & pricing | 10%12.5 | 45 | 53 | Tencent Cloud TokenHub +8 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 73 | 73 | even |
| Transparency & trust | 7%8.8 | 52 | 54 | Tencent Cloud TokenHub +2 |
| Negative events | ≤15 | 0 | -3 | |
| Total | B 64/100 | C 61.7/100 |
Facts side by side
| Fact | Tencent Hy4 | Tencent Cloud TokenHub |
|---|---|---|
| Kind | Model API | Model router |
| Vendor | Tencent (Hy team) | Tencent Cloud |
| Hosted endpoint | no (local only) | https://tokenhub.tencentmaas.com/v1 |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | Hosted model under the Tencent Cloud TokenHub terms. Tencent says weights and a system card will follow; no licence is stated yet | 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 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-11-04 | 2026-10-24 |
| Terms last updated | couldn't be read | couldn't be read |
| Privacy policy last updated | couldn't be read | couldn't be read |
| Customer content may train models | couldn't be read | couldn't be read |
| Terms restrict automated access | couldn't be read | couldn't be read |
| Terms restrict benchmarking | couldn't be read | couldn't be read |
| Terms or service can change without notice | couldn't be read | couldn't be read |
| Arbitration or class-action waiver | couldn't be read | couldn't be read |
| Popularity | none | 204 npm/wk |
How the scores have moved
Verdicts
Tencent Hy4
Tencent's flagship model is on TokenHub as hy4, with a 1M-token context, image understanding, function calling and caching, at ¥6 input and ¥18 output per million tokens, half price until the end of 2026. The weights it is called open source for aren't published yet, and every benchmark is Tencent's own.
Tencent Cloud TokenHub
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.
Before you call either
Tencent Hy4
- Use model id hy4 on TokenHub's OpenAI- or Anthropic-compatible endpoints; hy4-preview is a separate, older model
- Keep input under 960K tokens and expect at most 64K output
- Reuse prompt prefixes: cached input is ¥0.3 against ¥6
- Check the price page for the end of the 50% discount on 31 December 2026 before budgeting
- Read rate limits from the console or DescribeModelQuota; the public docs don't give them for chat models
Tencent Cloud TokenHub
- Use
https://tokenhub.tencentmaas.com/v1with keys made for Guangzhou andhttps://tokenhub-intl.tencentmaas.com/v1with keys made for Singapore. Keys do not work across the two - Send the key as
Authorization: Beareron the OpenAI paths and asx-api-keyon/v1/messages - Parse
error.codeas a string or a number, since 429 codes can come back as integers, and wait forRetry-Afterbefore retrying - Take model ids from
GET /v1/modelsand watch forpre-offline. The quickstart'sdeepseek-v3example 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
Questions
Which is better for AI agents, Tencent Hy4 or Tencent Cloud TokenHub?
Tencent Hy4 scores 64 (B) on agent readiness against Tencent Cloud TokenHub's 61.7 (C), and leads in 1 of 7 scored categories. Tencent Cloud TokenHub leads on payments & pricing.
Do Tencent Hy4 and Tencent Cloud TokenHub need an API key?
Both need an API key.
Can an agent call Tencent Hy4 and Tencent Cloud TokenHub without installing anything?
No hosted endpoint is listed for Tencent Hy4. Tencent Cloud TokenHub has a hosted endpoint at https://tokenhub.tencentmaas.com/v1.
Other comparisons with Tencent Hy4 or Tencent Cloud TokenHub
- Amazon Bedrock vs Tencent Hy4
- Amazon Bedrock vs Tencent Cloud TokenHub
- Claude API vs Tencent Hy4
- Claude API vs Tencent Cloud TokenHub
- Antseed vs Tencent Hy4
- Azure OpenAI in Foundry Models vs Tencent Hy4
- Azure OpenAI in Foundry Models vs Tencent Cloud TokenHub
- BlockRun.AI vs Tencent Hy4
- BlockRun.AI vs Tencent Cloud TokenHub
- Cerebras Inference vs Tencent Hy4
- Cerebras Inference vs Tencent Cloud TokenHub
- Claude Fable 5.2 vs Tencent Hy4
- Claude Fable 5.2 vs Tencent Cloud TokenHub
- Claude Mythos 5.2 vs Tencent Hy4
- Claude Mythos 5.2 vs Tencent Cloud TokenHub
- Cloudflare AI Gateway vs Tencent Hy4
- Cloudflare AI Gateway vs Tencent Cloud TokenHub
- Cloudflare Workers AI vs Tencent Hy4
- Cloudflare Workers AI vs Tencent Cloud TokenHub
- Cohere Chat API (Command models) vs Tencent Hy4
- Cohere Chat API (Command models) vs Tencent Cloud TokenHub
- DeepInfra vs Tencent Hy4
- DeepInfra vs Tencent Cloud TokenHub
- DeepSeek API vs Tencent Hy4
- DeepSeek API vs Tencent Cloud TokenHub
- Eden AI vs Tencent Hy4
- Glimpse vs Tencent Hy4
- Glimpse vs Tencent Cloud TokenHub
- Fireworks AI Inference vs Tencent Hy4
- Fireworks AI Inference vs Tencent Cloud TokenHub
- Gemini 4 Carbon vs Tencent Hy4
- Gemini 4 Carbon vs Tencent Cloud TokenHub
- Gemini 4 Hydrogen vs Tencent Hy4
- Gemini 4 Hydrogen vs Tencent Cloud TokenHub
- Gemini Developer API vs Tencent Hy4
- Gemini Developer API vs Tencent Cloud TokenHub
- GroqCloud vs Tencent Hy4
- GroqCloud vs Tencent Cloud TokenHub
- Hugging Face Inference Providers vs Tencent Hy4
- Tencent Hy4 vs Jais 3
- Tencent Hy4 vs Meta Model API
- Tencent Hy4 vs MiniMax API
- Tencent Hy4 vs Mistral AI API
- Tencent Hy4 vs Muse Ember
- Tencent Hy4 vs Muse Spark Open
- Tencent Hy4 vs Nemotron 3.5 Super VL
- Tencent Hy4 vs Novita AI
- Tencent Hy4 vs OpenAI API
- Tencent Hy4 vs OpenRouter
- Tencent Hy4 vs Prism Inference
- Tencent Hy4 vs Router.com (Ramp Router)
- Tencent Hy4 vs Beam 1.0
- Tencent Hy4 vs RouterPlus
- Tencent Hy4 vs SambaCloud
- Tencent Hy4 vs SiliconFlow
- Tencent Hy4 vs Simplismart
- Tencent Hy4 vs StepFun API
- Tencent Hy4 vs SWE-2 Flash
- Tencent Hy4 vs Together AI Inference
- Tencent Hy4 vs Vercel AI Gateway
- Tencent Hy4 vs Vertex AI (Gemini Enterprise Agent Platform)
- Tencent Hy4 vs xAI API (Grok)
- Jais 3 vs Tencent Cloud TokenHub
- Meta Model API vs Tencent Cloud TokenHub
- MiniMax API vs Tencent Cloud TokenHub
- Mistral AI API vs Tencent Cloud TokenHub
- Muse Ember vs Tencent Cloud TokenHub
- Muse Spark Open vs Tencent Cloud TokenHub
- Novita AI vs Tencent Cloud TokenHub
- OpenAI API vs Tencent Cloud TokenHub
- OpenRouter vs Tencent Cloud TokenHub
- Beam 1.0 vs Tencent Cloud TokenHub
- SambaCloud vs Tencent Cloud TokenHub
- SiliconFlow vs Tencent Cloud TokenHub
- Simplismart vs Tencent Cloud TokenHub
- StepFun API vs Tencent Cloud TokenHub
- SWE-2 Flash vs Tencent Cloud TokenHub
- Tencent Cloud TokenHub vs Together AI Inference
- Tencent Cloud TokenHub vs Vertex AI (Gemini Enterprise Agent Platform)
- Tencent Cloud TokenHub vs xAI API (Grok)
- Antseed vs Tencent Cloud TokenHub
- Eden AI vs Tencent Cloud TokenHub
- Hugging Face Inference Providers vs Tencent Cloud TokenHub
- LiteLLM vs Tencent Cloud TokenHub
- Router.com (Ramp Router) vs Tencent Cloud TokenHub
- RouterPlus vs Tencent Cloud TokenHub
- Tencent Cloud TokenHub vs Vercel AI Gateway
- Nemotron 3.5 Super VL vs Tencent Cloud TokenHub
- Prism Inference vs Tencent Cloud TokenHub
Machine-readable
- This page as Markdown
/compare/hy4-vs-tencent-tokenhub.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/hy4.json·/api/v1/tools/tencent-tokenhub.json - From a terminal
anchor compare hy4 tencent-tokenhub(the CLI) - Over MCP
compare_tools {"a": "hy4", "b": "tencent-tokenhub"}at/mcp, no key