Loading tool…
One OpenAI-compatible endpoint fronting OpenAI, Anthropic, Google and DeepSeek at discounted token rates
TokenHot is an API gateway: point an OpenAI-compatible client at a single endpoint and key, then switch between models from OpenAI, Anthropic, Google, DeepSeek, Qwen, ByteDance, MiniMax and Z.ai without rewriting your integration. It publishes a side-by-side rate table pitching its own per-million-token price against each vendor's list price, and bills strictly pay-as-you-go with no KYC and no subscription. Setup guides cover Claude Code, Cherry Studio and Hermes Agent, and the site shows live latency probes from Singapore, Japan, Korea, India, the US and Europe. The footer says TokenHot Inc.; no country, address or registered jurisdiction appears anywhere.
Metered per token, not per plan: rates are quoted per million input and output tokens and vary by model, from about $0.04 per million input on the cheapest model up to $1.70 for Claude Opus 5 input. There is no subscription tier and no published minimum top-up, so no plan entry price exists.
Use tool ↗The pitch is straightforward: the same frontier models through one endpoint at a large discount to list price, with no account verification. That combination is exactly what should make you cautious — steeply discounted resale of first-party model access, from a vendor that names no jurisdiction, is a supply chain you cannot audit.
Watch out: Routing prompts through an anonymous reseller means your traffic and any data in it leave your control before reaching the model vendor — check your own compliance rules first.
No reviews yet — be the first to review Tokenhot AI.
Reviews are tied to your EffectHub account — one review per tool, so the rating for Tokenhot AI reflects real users.
No questions yet — ask the first one about Tokenhot AI.
Questions about Tokenhot AI are tied to your EffectHub account, so answers can reach you and the section stays free of spam.