# hy3 API

Tencent's hy3, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send hy3 as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

## Facts

- Model name: hy3
- Maker: Tencent
- Context window: 262.1K tokens
- Input price: $0.066 per million tokens
- Output price: $0.260 per million tokens
- Providers: 1 independent provider
- Regions: us

## Providers

- [Architect](https://liquidinference.ai/providers/805445a7-0e40-4c1b-9baf-7b3b01e30e42.md): us, $0.066 input and $0.260 output per million tokens, $0.029 cache read per million tokens, 262.1K tokens of context

## Request

```sh
curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy3",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is hy3?

Served by intent-router: each job goes to the cheapest healthy upstream for this model.

### How much does hy3 cost?

Offers now ask $0.066 per million input tokens and $0.260 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.

### What is the context length of hy3?

The largest offer takes 262,144 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can hy3 do?

Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.

### What inputs and outputs does hy3 support?

Text → Text.

### Which providers serve hy3?

1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.

### How do I call hy3?

Send "hy3" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was hy3 listed?

The exchange first listed it on 10/8/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/hy3)
- [hy4](https://liquidinference.ai/models/hy4.md)
- [hy4 Preview](https://liquidinference.ai/models/hy4-preview.md)
- [Set up a client](https://liquidinference.ai/connect/hy3)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)