# Hy3 API, priced in naira

URL: https://bridge.wekoya.tech/models/hy3
Updated: 2026-11-08

**In short:** You can use Hy3, a model by Tencent, from Nigeria through Bridge and pay in naira, with no dollar card. It costs ₦228 per million input tokens and ₦930 per million output tokens. Call it with the OpenAI SDK using the model ID `hy3`.

## Price and limits

|   | Hy3 |
| --- | --- |
| Input, per million tokens | ₦228 |
| Output, per million tokens | ₦930 |
| Cached input, per million tokens | ₦57.92 |
| Writing to the cache, per million tokens | ₦228 |
| Context window | 262,144 tokens |
| Longest reply | 16,384 tokens |
| Reads pictures | No |
| Tool calling | Yes |
| Reasoning (thinks before it answers) | Yes |
| Model ID | `hy3` |

Prices as of 8 November 2026. They are in naira and follow the exchange rate, so the [live price](https://bridge.wekoya.tech/models/hy3) 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 ₦0.807 on 8 November 2026. A thousand of them cost about ₦807. 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 ₦0.637.

## Use Hy3 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 `hy3` 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="hy3",
    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 |
| --- | --- | --- | --- |
| [Hy4 preview](https://bridge.wekoya.tech/models/hy4-preview) | ₦1,464 | ₦4,389 | 1,048,576 |

[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 Hy3 and can also call tools, reason and take at least 262,144 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 |
| --- | --- | --- | --- |
| [Qwen3.8 Flash](https://bridge.wekoya.tech/models/qwen3-8-flash) | ₦198 | ₦670 | 1,000,000 |
| [MiMo-V2.6-Flash](https://bridge.wekoya.tech/models/mimo-v2-6-flash) | ₦246 | ₦491 | 1,048,576 |
| [GPT-6 Luna](https://bridge.wekoya.tech/models/gpt-6-luna) | ₦149 | ₦743 | 1,050,000 |
| [Claude Haiku 5.5](https://bridge.wekoya.tech/models/claude-haiku-5-5) | ₦149 | ₦743 | 1,000,000 |

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

## Common questions

**How much does Hy3 cost in naira?**

On Bridge, Hy3 costs ₦228 per million input tokens and ₦930 per million output tokens, with cached input at ₦57.92 (as of 8 November 2026). A request that sends 1,500 tokens and gets 500 back costs about ₦0.807. There is no subscription and no minimum.

**Can I use the Hy3 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 Hy3 with your Bridge key. A card works too, but it is not needed.

**Does Hy3 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 hy3. Streaming works, and so does tool calling.

**What is the context window of Hy3?**

262,144 tokens, about 196,608 words of instructions, conversation and documents together. It writes up to 16,384 tokens in one reply.

**Can Hy3 read pictures?**

No. Hy3 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)