# Hy3 API Pricing

As of October 10, 2026, Hy3 costs $0.14 per 1M input tokens and $0.58 per 1M output tokens from Novita AI, the lowest of 3 providers, with cache reads at $0.035 per 1M tokens. It has a 262,144-token context window and returns up to 262,144 tokens per response.

- Page: https://models.litellm.ai/models/hy3
- LiteLLM model name: `novita/tencent/hy3`
- Context window: 262,144 tokens
- Max output: 262,144 tokens
- Added to LiteLLM: August 27, 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Novita AI | `novita/tencent/hy3` | $0.14 | $0.58 | $0.035 | – | – | 256K |
| AIHubMix | `aihubmix/hy3` | $0.1562 | $0.6248 | $0.03905 | – | – | 256K |
| DeepInfra | `deepinfra/tencent/Hy3` | $0.14 | $0.58 | $0.035 | – | – | 256K |

## Cost examples

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

- Novita AI: $0.57
- DeepInfra: $0.57
- AIHubMix: $0.6248

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

- Novita AI: $1.516
- DeepInfra: $1.516
- AIHubMix: $1.687

## Features

Supported: Function calling, Structured output, Reasoning, Prompt caching, Web search.
Not supported: Image input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="novita/tencent/hy3",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Hy3 cost?

Hy3 costs $0.14 per 1M input tokens and $0.58 per 1M output tokens from Novita AI, the lowest of 3 providers, with cache reads at $0.035 per 1M tokens.

### What is the context window of Hy3?

Hy3 has a 262,144-token context window and returns up to 262,144 tokens per response.

### Which providers offer Hy3?

Hy3 is available from 3 providers through LiteLLM: Novita AI, AIHubMix and DeepInfra. The lowest price is on Novita AI.

### How do I call Hy3 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="novita/tencent/hy3", 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 Hy3 support?

Hy3 supports function calling, structured output, reasoning, prompt caching and web search. It does not support image input.

### When did LiteLLM add Hy3?

Hy3 was added to LiteLLM's model price file on August 27, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json