HardysAPIAuthenticity, speed and price analysis
About the site
HardysAPI 是按量计费的统一 AI API 网关,兼容 OpenAI / Anthropic / Gemini 原生协议,
19 条线路、100+ 模型,倍率 0.08x–4x。文本按 token、生图按张,1 元 = 1 美元额度,
10 元起充,支付宝 / 微信。多账号池调度,不承诺 99.9% SLA,异常需手动切分组。
售后:support@hardysapi.com,安全问题 24 小时内响应。
Service details
- Minimum top-up¥10
- Sign-up bonus¥0.1
- Support response8小时内
- Payment methodsWeChat Pay, Alipay, USDT, Other
- China invoiceNot applicable
- International invoiceNot applicable
- RefundsNot supported
- Promotions充值赠送10%,最高可赠送20%
(seconds)
coding session
availability
Comparison summary
Gemini 4 Argon on HardysAPI: a coding session costs ¥3.52, ranking 9 of 16 (median ¥3.52).
Authenticity
Model consistency
Output distribution for the same requests on this relay and on the official API · higher is better
Speed
Measured by time to first token (seconds) and output speed (tokens / second)
Time to first token
Seconds until the first token · lower is better
Price
Groups and models
| Group | Model | Availability | Input price | Output price | Pricing unit |
|---|---|---|---|---|---|
| Gemini-vertex | Gemini 4 Argon | Not probed yet | ¥1.60 | ¥8.00 | Per million tokens |
| Gemini 全能(波动大) | Gemini 4 Argon | Not probed yet | ¥1.20 | ¥6.00 | Per million tokens |
Cost per coding session
Gemini 4 Argon · 2M input and 40k output tokens (¥) · split by token type · lower is better
Prices: cache hit, input and output
¥ / 1M tokens
Cache
Coding requests repeat much of their context, so the cache hit rate largely decides what you actually pay. Drag the hit rate and the costs and ranking below are reweighted with cache prices.
Cache-weighted session cost
Gemini 4 Argon · of 2M input tokens, the hit share is billed at the cache price and the rest at the input price, plus 40k output (¥) · lower is better
Stability
Availability
Request success rate, last 24 hours · higher is better
Status of each model, last 24 hours
One cell per hour · green ok, yellow delayed, red failed
FAQ
How much does Gemini 4 Argon cost on HardysAPI?
Input ¥1.6 and output ¥8 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥3.52, an API rate of 0.12.
How does the cache hit rate affect price?
HardysAPI has not published a cache price for this route, so cache hits are billed at the input price.Measured hit rates will replace this assumption once available.
Which models does HardysAPI support?
Folkbench currently lists 51: Claude Fable 5, Claude Opus 4.8, Claude Opus 5, GLM 5.3 Flash, GPT 5.6 Sol, Claude Sonnet 5, GPT 5.6 Terra, Kimi K3, GLM 5.3, Grok 4.6, Claude Opus 4.7, Gemini 3.8 Flash, Claude Haiku 4.5, Gemini 4 Argon, Claude Sonnet 4.6, Claude Opus 4.6, Grok 4.5, DeepSeek V4 Pro, GPT 5.6 Luna, Qwen 3.8 Max, GLM 5.2, Qwen 3.8 Flash, Claude Opus 4.5, MiniMax M3, GPT 5.5, Claude Sonnet 4.5, Qwen 3.7 Max, DeepSeek V4 Flash, Kimi K2.7 Code, DeepSeek V4 Pro 0813, DeepSeek V4 Flash 0731, Kimi K2.6, GPT-4o Mini, GLM 5.1, Qwen 3.7 Plus, GPT 5.2, GPT 5.4, GPT 5.4 Mini, GPT-4o, GPT 5.3 Codex, Gemini 3 Flash, GPT 4.1, GPT 5, GPT 4.1 Mini, GPT 5 Nano, Qwen 3.5 Plus, GPT 5 Mini, o3, Qwen 3.6 Plus, GPT 5.2 2025-12-11, GPT 5.4 2026-03-05.
What does the data security level mean?
Folkbench rates relays from 0 to 4 based on public policies and verifiable evidence; HardysAPI is currently level 0. The check covers leaks in responses and error messages only, and does not prove data retention or training policies.
How often is this data updated?
Availability and time to first token use a 24-hour window, and this page syncs live data every 15 minutes.