点名模
下方中国名模适合点名调用；国际旗舰为附属。倍率越高，余额消耗越快。优先用 flash（$0.35/百万起）；DeepSeek 点名为 V4.1 Flash（峰谷价），V4 Pro 自 9/14 起官方并轨 Flash 计费。
点名模按输入/输出双费率计费（表格列出 in/out 每百万单价）；品牌档 flash/pro/auto 仍单费率。输出重负载（coding / agent / 长文）请先核算输出价。
怎么用
- 注册并创建 API Key
- 在价格页或控制台购买套餐（点名模需套餐含 VIP）
- 请求里填写模型名：优先用推荐档；也可填下方名模名称
推荐档（优先）
Start with flash ($0.35/M) or pro; prefer flash for agents/tools. auto can use tools when you have balance; after credits run out the free daily pool is text-only. Named models drain prepaid credits faster. Costs are estimates.
| 分组 | 名称 | 模型名 | 倍率 | 预估消耗 | 工具 | 视觉 | 说明 |
|---|---|---|---|---|---|---|---|
| … | |||||||
名模点名
认准某一款时再点名（需套餐含 VIP）。倍率通常更高；预估消耗仅供参考，会随服务更新。
| 分组 | 名称 | 模型名 | 倍率 | 预估消耗 | 工具 | 说明 | 🖼️ |
|---|---|---|---|---|---|---|---|
| Loading… | |||||||
调用示例
名模点名需 VIP。高峰时可能自动改用推荐档，以保证可用。
When to request a model by name
- You need a specific model's behaviour, not "a good enough answer" — pick by name.
- You're benchmarking or migrating from a direct provider — pick by name to keep parity.
- You just want the cheapest capable answer — use
flash/proand let routing work.
Start with one key
One API key covers DeepSeek, Qwen, GLM, Kimi, MiniMax, MiMo and frontier models — on a flat rate with no peak-hour surcharge and no request-size price tiers. Payment is by PayPal or card, and no Chinese phone number is required.
Frequently asked questions
Can I use the VIP picks API outside China without a Chinese phone number?
Yes. AI24X provides OpenAI-compatible access through one endpoint (https://api.ai24x.com/v1). Signup does not require a Chinese phone number and payment is accepted by PayPal or card.
Does AI24X charge a peak-hour surcharge?
No. AI24X bills a flat rate with no peak/off-peak window surcharge and no request-size price tiers.
Is AI24X the official VIP picks API?
No. AI24X is an independent AI gateway and is not affiliated with any model provider. Model names describe compatibility only.