# Hy4 preview API, priced in naira

URL: https://bridge.wekoya.tech/models/hy4-preview
Updated: 2026-11-08

**In short:** You can use Hy4 preview, a model by Tencent, from Nigeria through Bridge and pay in naira, with no dollar card. It costs ₦1,464 per million input tokens and ₦4,389 per million output tokens. Call it with the OpenAI SDK using the model ID `hy4-preview`.

## Price and limits

|   | Hy4 preview |
| --- | --- |
| Input, per million tokens | ₦1,464 |
| Output, per million tokens | ₦4,389 |
| Cached input, per million tokens | ₦73.71 |
| Writing to the cache, per million tokens | ₦1,464 |
| Context window | 1,048,576 tokens |
| Longest reply | 16,384 tokens |
| Reads pictures | No |
| Tool calling | Yes |
| Reasoning (thinks before it answers) | Yes |
| Model ID | `hy4-preview` |

Prices as of 8 November 2026. They are in naira and follow the exchange rate, so the [live price](https://bridge.wekoya.tech/models/hy4-preview) may differ a little. A token is roughly three quarters of a word.

## What a request costs

A request that sends 1,500 tokens (instructions, the conversation so far and a question) and gets 500 back (about 375 words) costs about ₦4.39 on 8 November 2026. A thousand of them cost about ₦4,390. When 1,000 of the input tokens are instructions that stay the same, [prompt caching](https://bridge.wekoya.tech/docs/prompt-caching) reads them at the cached rate and the request costs about ₦3.00.

## Use Hy4 preview from your code

Bridge speaks the OpenAI format, so the OpenAI SDK works as it is: set the base URL to `https://wekoya-api.wekoya.tech/v1`, use your Bridge key, and pass `hy4-preview` as the model. [Create a key](https://bridge.wekoya.tech/sign-up), then:

```python
from openai import OpenAI

client = OpenAI(api_key="wk_live_...", base_url="https://wekoya-api.wekoya.tech/v1")
reply = client.chat.completions.create(
    model="hy4-preview",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)
```

Streaming works the same way, and so does [tool calling](https://bridge.wekoya.tech/docs/tools). The [quickstart](https://bridge.wekoya.tech/docs) has the same in JavaScript and curl, and the [Responses API](https://bridge.wekoya.tech/docs/responses) works too.

## Other Tencent models on Bridge

| Model | Input / 1M | Output / 1M | Context |
| --- | --- | --- | --- |
| [Hy3](https://bridge.wekoya.tech/models/hy3) | ₦228 | ₦930 | 262,144 |

[Every Tencent model on Bridge](https://bridge.wekoya.tech/models/tencent), with what each can do.

## Lower-priced models that can do the same things

These cost less per request than Hy4 preview and can also call tools, reason and take at least 1,048,576 tokens of context. Quality differs from model to model, so test on your own examples first: [AI tasks](https://bridge.wekoya.tech/docs/workloads) compares models on your cases and tells you whether a cheaper one is good enough.

| Model | Input / 1M | Output / 1M | Context |
| --- | --- | --- | --- |
| [GLM-5.3](https://bridge.wekoya.tech/models/glm-5-3) | ₦988 | ₦4,388 | 1,048,576 |
| [GLM-5.2](https://bridge.wekoya.tech/models/glm-5-2) | ₦986 | ₦3,159 | 1,048,576 |
| [Gemini 3.5 Flash Lite](https://bridge.wekoya.tech/models/gemini-3-5-flash-lite) | ₦446 | ₦3,713 | 1,048,576 |
| [MiMo-V2.6-Pro](https://bridge.wekoya.tech/models/mimo-v2-6-pro) | ₦679 | ₦1,374 | 1,048,576 |

[Create a free account](https://bridge.wekoya.tech/sign-up)

## Common questions

**How much does Hy4 preview cost in naira?**

On Bridge, Hy4 preview costs ₦1,464 per million input tokens and ₦4,389 per million output tokens, with cached input at ₦73.71 (as of 8 November 2026). A request that sends 1,500 tokens and gets 500 back costs about ₦4.39. There is no subscription and no minimum.

**Can I use the Hy4 preview API from Nigeria without a dollar card?**

Yes. Create a free Bridge account, top up your naira balance by bank transfer to your own account number, and call Hy4 preview with your Bridge key. A card works too, but it is not needed.

**Does Hy4 preview on Bridge work with the OpenAI SDK?**

Yes. Use the OpenAI SDK or any OpenAI-compatible client with the base URL https://wekoya-api.wekoya.tech/v1 and the model ID hy4-preview. Streaming works, and so does tool calling.

**What is the context window of Hy4 preview?**

1,048,576 tokens, about 786,432 words of instructions, conversation and documents together. It writes up to 16,384 tokens in one reply.

**Can Hy4 preview read pictures?**

No. Hy4 preview reads text only. For pictures, pick a model marked "Reads pictures" on the models page.

## Read next

- [All models and prices](https://bridge.wekoya.tech/models)
- [Quickstart](https://bridge.wekoya.tech/docs)
- [Pay for AI APIs from Nigeria](https://bridge.wekoya.tech/guides/pay-for-ai-apis-in-nigeria)