- Site domain
- tokenonly.ai
- Established
- 2026-05-01
- Covered models
- Under review
- Public records
- 0 public records
- User feedback
- 0 up / 0 down
Site descriptions, notices, and reviews are shown in the language in which they were submitted.
Site introduction
TokenOnly 解决的核心问题是：如何以最低摩擦、最低成本、最高可靠性使用多家 LLM 厂商的模型。 对于国内开发者而言，它额外解决了一个长期痛点——稳定的国内直连，让 Claude / GPT / Gemini 的调用和访问国内 API 一样顺畅。 我们和其他平台的根本差异在于：原生协议，不是强行兼容。你调用的是真正的 Claude，而不是一个被包装过的模拟器。 如果你在用 Claude Code、Cursor、Codex CLI 做 AI 编程，或者正在开发需要调用多家模型 API 的产品，TokenOnly 值得一试。
Model coverage summary
No public probe summary is available for this gateway yet. It will be updated with future ranking data.
Public model pricing
Current public prices are shown by model and channel. Token prices use CNY per 1M tokens unless another billing unit is shown.
No public price is available yet.
How to read this data
Uptime is the share of recent probes where the service was available; a higher value generally indicates better stability.
Model consistency uses model pass results to show whether the endpoint behaves like the target model.
Pricing and latency come from public monitoring data and are intended for side-by-side gateway comparison.
Data is provided for reference. Third-party gateways may experience outages or balance loss, so test first and add only a small balance when needed.