# Hy4 API Pricing

As of November 7, 2026, Hy4 costs $0.417 per 1M input tokens and $1.25 per 1M output tokens from GMI Cloud, the lowest of 2 providers, with cache reads at $0.021 per 1M tokens. It has a 1,000,000-token context window and returns up to 64,000 tokens per response.

- Page: https://models.litellm.ai/models/hy4
- LiteLLM model name: `gmi/tencent/hy4`
- Context window: 1,000,000 tokens
- Max output: 64,000 tokens
- Added to LiteLLM: November 5, 2026
- Prices updated: November 6, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| GMI Cloud | `gmi/tencent/hy4` | $0.417 | $1.25 | $0.021 | – | – | 1M |
| Tencent TokenHub | `tencent/hy4` | $0.834 | $2.501 | $0.042 | – | – | 960K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- GMI Cloud: $1.459
- Tencent TokenHub: $2.918

100 long-document requests with 100,000 input and 2,000 output tokens each:

- GMI Cloud: $4.42
- Tencent TokenHub: $8.84

## Features

Supported: Function calling, Structured output, Image input, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="gmi/tencent/hy4",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## Cost calculator

10,000 requests a day with 1,000 input and 500 output tokens each, at GMI Cloud's price: $0.001042 per request, $10.42 per day, $313 per month (30 days). Try other numbers at https://models.litellm.ai/calculator?model=hy4

## FAQ

### How much does Hy4 cost?

Hy4 costs $0.417 per 1M input tokens and $1.25 per 1M output tokens from GMI Cloud, the lowest of 2 providers, with cache reads at $0.021 per 1M tokens.

### What is the context window of Hy4?

Hy4 has a 1,000,000-token context window and returns up to 64,000 tokens per response.

### Which providers offer Hy4?

Hy4 is available from 2 providers through LiteLLM: GMI Cloud and Tencent TokenHub. The lowest price is on GMI Cloud.

### How do I call Hy4 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gmi/tencent/hy4", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Hy4 support?

Hy4 supports function calling, structured output, image input, reasoning and prompt caching.

### When did LiteLLM add Hy4?

Hy4 was added to LiteLLM's model price file on November 5, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change.