ClaudeCN
claudecn.top
ClaudeCN is a relay at claudecn.top. In the 7-day window ending 2026-11-14, our probes measured 96.0% uptime and 4.75s average latency across 428 samples. The public availability grade is C. The snapshot marks this profile for observation: the grade is not A, the sample is thin, or both. The lowest listed input price in the snapshot is ¥0.8 per 1M tokens.
7-day window ending 2026-11-14 · 428 probe samples · Chinese profile: 完整中文档案
What the grade means
AVAILABILITY ONLYGrade C means the site did not meet the B threshold: uptime below 97%, latency above 6.5 seconds, or too little data.
The risk flag is derived from the grade and the sample. Watch — grade B, grade A with a thin sample, or grade C with uptime at or above 95%.
The availability score is 0.75 × uptime + 0.25 × max(0, 100 − latency × 8). It orders sites inside the same window only. A profile with 428 samples carries less confidence than one with thousands; below 200 samples we say watch, not recommended.
Model coverage in the snapshot
Anthropic Claude, DeepSeek, Zhipu GLM, OpenAI GPTModel families recorded on this site: Anthropic Claude, DeepSeek, Zhipu GLM, OpenAI GPT. The table lists model IDs that the coverage map matched to this host. A missing row means no match, not that the site lacks the model.
| Model | Listed relay price / 1M |
|---|---|
| DeepSeek Chat | ¥1.8 |
| DeepSeek R1 0528 | ¥3.6 |
| DeepSeek Reasoner | ¥3.6 |
| DeepSeek V3 0324 | ¥1.8 |
| DeepSeek V3.2 | ¥1.8 |
| DeepSeek V4 Flash 0731 | ¥2.7 |
| DeepSeek V4 Flash Vision Exp | ¥67.5 |
| DeepSeek V4.1 Flash 1017 | — |
| DeepSeek-R1 | ¥3.6 |
| DeepSeek-R1-Distill-Qwen-32B | ¥1.8 |
| DeepSeek-V3 | ¥1.8 |
| DeepSeek-V3.1 | ¥3.6 |
| Doubao-Seedance-1.5-pro | ¥13.95 |
| Doubao-Seedance-2.0 | ¥0.0234 |
| GLM-4.5 | ¥0.54 |
| GLM-4.5-Air | ¥0.72 |
| GLM-4.6 | ¥0.54 |
| GLM-4.6V | ¥0.9 |
| GLM-4.7 | ¥1.8 |
| GLM-5 | ¥3.6 |
| GLM-5 Turbo | ¥4.5 |
| GLM-5V-Turbo | ¥4.5 |
| GPT 6 Luna | ¥0.05–¥0.7 |
| GPT OSS 120B | ¥7.7 |
| GPT-3.5-turbo | ¥3.5 |
| GPT-4 | ¥210 |
| GPT-4 Turbo | ¥70 |
| GPT-4.1 | ¥14 |
| GPT-4.1 mini | ¥2.8 |
| GPT-4.1 nano | ¥0.7 |
| GPT-4o | ¥17.5 |
| GPT-4o (2024-05-13) | ¥35 |
| GPT-4o (2024-08-06) | ¥17.5 |
| GPT-4o (2024-11-20) | ¥17.5 |
| GPT-4o mini | ¥1.05 |
| GPT-5 | ¥8.75 |
| GPT-5 Chat | ¥8.75 |
| GPT-5 mini | ¥1.75 |
| GPT-5 Nano | ¥0.35 |
| GPT-5 Pro | ¥105 |
Showing the first 40 of 122 model IDs linked to this host in the coverage snapshot.
Payments and paperwork
AS RECORDEDPayments recorded: Alipay, Bank transfer, Credit card. Refund policy recorded: no. Invoice support recorded: yes. Not verified in the snapshot.
These fields come from the public directory snapshot, not from a contract review. Confirm them on the site before paying.
What this page does not claim
BOUNDARY- It does not claim the site is safe, honest, or compliant. We do not audit corporate ownership, fund custody, data handling, or licences.
- It does not claim the models are genuine. Model authenticity requires the seven checks; availability does not answer it.
- It does not claim 24/7 monitoring. A probe window is a sample, and results can change by time of day.
- It is not a paid placement. Certification covers verification and retesting; it does not change the grade or the order of this directory.
Questions
FAQIs ClaudeCN reliable?
We publish what we measured: 96.0% uptime and 4.75s average latency across 428 samples in the 7-day window. That is an availability observation, not a recommendation. We do not audit ownership, fund custody, data handling, or licensing.
What does grade C mean?
Grade C means the site did not meet the B threshold: uptime below 97%, latency above 6.5 seconds, or too little data. Detection failures are not folded into this grade yet.
Does ClaudeCN serve the models it advertises?
The directory records advertised model IDs. To test whether a relay serves the genuine model, run the seven checks with a key you control. A single run is a spot check; results can change by time of day.
How do I test ClaudeCN myself?
Open the detection page, enter the site's base URL and a key, and run the checks. The key is used for the request and is not stored. You can also compare this profile with other sites in the directory.