Hunyuan API

Tencent's Hunyuan (HY) models through Tencent Cloud's TokenHub, with OpenAI- and Anthropic-compatible endpoints in Singapore, the US and mainland China.

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

The Hunyuan API is how you call Tencent's Hunyuan models, now branded HY: the Hy3 language model and a Hy4 preview, plus vision and translation models on the mainland site. Internationally they're sold through TokenHub, Tencent Cloud's model service, which also serves DeepSeek, GLM, Kimi and MiniMax models under the same account. Tencent's older standalone Hunyuan console on its mainland China cloud no longer takes new purchases.

Every TokenHub model accepts both the OpenAI Chat Completions format and the Anthropic Messages format, so you use the official OpenAI or Anthropic SDKs by swapping the base URL and key. Each region has its own endpoint: https://tokenhub-intl.tencentcloudmaas.com/v1 for Singapore, https://tokenhub-us.tencentcloudmaas.tech/v1 for Silicon Valley, and https://tokenhub.tencentcloudmaas.com/v1 for Guangzhou in mainland China. Hy3 is called as hy3.

Useful for a small team: one key covers Tencent's models and several other Chinese model families; Hy3 is published as open weights on Hugging Face under Apache 2.0, so you can serve it yourself; and Token Plan subscriptions are sold alongside pay-per-token billing.

Limits: Tencent, based in Shenzhen, processes data in the service region you select, but its data processing agreement lets it process data outside that region for operational, regulatory or other reasons. Prices also differ by region, so choose one before you build.

Where it fits

Who uses it

No maker's live product on record yet.

We haven't found a product that uses Hunyuan API yet.

Alternatives to Hunyuan API

All alternatives by situation →

Questions makers ask about Hunyuan API

Which endpoints and SDKs can I use?

TokenHub accepts the OpenAI Chat Completions and Anthropic Messages formats for all models. OpenAI-style calls send Authorization Bearer with your key, Anthropic-style calls send x-api-key, against the Singapore, Silicon Valley or Guangzhou base URL. source ↗

Where is my data processed?

Under Tencent Cloud's data processing agreement, if you select a service region Tencent processes personal data in that region, though the agreement allows processing outside it for operational, regulatory or other reasons. Prices also differ by region, so choose one before you build. source ↗

What happens when I hit a rate limit?

TokenHub returns a 429-series error code, sometimes with a Retry-After header, and Tencent recommends retrying with exponential backoff. source ↗

Which other models are on TokenHub?

Besides Tencent's own HY models, TokenHub serves models from DeepSeek, MiniMax, Kimi and Zhipu GLM through the same API. source ↗

Can I run Hunyuan myself?

Hy3 is published by Tencent on Hugging Face under the Apache 2.0 license, so you can serve it on your own hardware. source ↗

How much does Hunyuan API cost?

Paid use starts at Pay per token. source ↗

Is Hunyuan API open source or self-hostable?

Not open source, and hosted only.

Can AI coding agents work with Hunyuan API?

No llms.txt, official MCP server or CLI found yet.

Who uses Hunyuan API?

No tracked product yet. source ↗