DragonAPI
newapi.dragon3api.com
DragonAPI is a relay at newapi.dragon3api.com. In the 7-day window ending 2026-11-14, our probes measured 97.9% uptime and 7.02s average latency across 552 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 ¥0.12 per 1M tokens.
7-day window ending 2026-11-14 · 552 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 552 samples carries less confidence than one with thousands; below 200 samples we say watch, not recommended.
Model coverage in the snapshot
DeepSeek, Zhipu GLM, OpenAI GPT, OtherModel families recorded on this site: DeepSeek, Zhipu GLM, OpenAI GPT, Other. 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 |
|---|---|
| Claude Fable 5.1 | ¥2.2–¥12 |
| Claude Haiku 4.5 | ¥0.1–¥0.22 |
| Claude Opus 4.5 | ¥0.5–¥1.1 |
| Claude Opus 4.6 | ¥0.5–¥1.1 |
| Claude Opus 4.7 | ¥0.5–¥1.1 |
| Claude Opus 4.8 | ¥0.5–¥1.1 |
| Claude Sonnet 4.5 | ¥0.3–¥0.66 |
| Claude Sonnet 4.6 | ¥0.3–¥0.66 |
| Claude Sonnet 5 | ¥0.2–¥2.4 |
| DeepSeek V4 Flash | ¥0.3 |
| GLM 5.1 | ¥1.2 |
| GLM 5.2 | ¥1.2 |
| GPT Image 2.5 Flare | ¥0.04 |
| GPT Image 2.5 Sunburst | ¥0.04 |
| Grok 4.6 | ¥0.3 |
| Grok Imagine Image | ¥0.2 |
| Grok Imagine Image 2.0 | ¥0.2 |
| Grok Imagine Image Quality | ¥0.2 |
| Hy3 | ¥0.15 |
| Hy4 Preview | ¥0.9 |
| Kimi K2.7 Code | ¥0.975 |
| MiMo-V2.5 | ¥0.15 |
| MiMo-V2.5-Pro | ¥0.465 |
| MiMo-V2.6-Flash | ¥0.15 |
| MiniMax M2.7 | ¥0.315 |
| MiniMax M3 | ¥0.315 |
| MiniMax-M2.7-highspeed | ¥0.63 |
| Nano Banana Pro Preview | ¥0.12 |
| NanoBanana 2 | ¥0.12 |
| Opus 5 | ¥0.5–¥1.1 |
| Qwen3.7 Max | ¥1.8 |
| Qwen3.8 Flash | ¥0.12 |
| Qwen3.8 Max | ¥1.8 |
Payments and paperwork
AS RECORDEDPayments recorded: WeChat Pay, Alipay, Bank transfer. Refund policy recorded: yes. Invoice support recorded: yes. Enterprise verification.
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 DragonAPI reliable?
We publish what we measured: 97.9% uptime and 7.02s average latency across 552 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 DragonAPI 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 DragonAPI 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.