Tencent models, priced in toman
8 Tencent models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Tencent on uttapen
Tencent currently has 8 models in the uttapen catalogue. All of them bill against a toman wallet, for the tokens a request actually used.
The spread inside Tencent alone is wide: Hy-MT2-1.8B runs about 99 toman for a 1,000-word request, while Hy4 preview costs 1,501 toman for the same one. Picking the right model inside a brand matters as much as picking the brand.
Measured against the whole catalogue, the median Tencent output price undercuts about 74% of the other paid models.
On capabilities: 1 takes image input, 4 support tool calling, 5 do multi-step reasoning. The longest context belongs to Hy4, at 1,048,576 tokens.
Every Tencent model answers on the same sk-up- key and the same base_url: switching between them means changing the `model` string and nothing else.
Which Tencent model should I start with?
- Hy-MT2-1.8B99 · per 1,000 wordsThe cheapest way in: about 99 toman for a 1,000-word request.
- Hy3297 · per 1,000 wordsThe cheapest Tencent model with tool calling — for agents and for wiring the model to your own API.
- Hy4751 · per 1,000 wordsFor multi-step problems, maths and debugging: it reasons before it answers.
Every Tencent model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Hunyuan A13B Instructtencent/hunyuan-a13b-instruct | ReasoningJSON output | 131,072 | 48,471 | 197,345 |
Hy-MT2-1.8Btencent/hy-mt2-1.8b | 8,192 | 15,234 | 61,281 | |
Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b | JSON output | 8,192 | 25,620 | 102,135 |
Hy-MT2-7Btencent/hy-mt2-7b | JSON output | 8,192 | 25,620 | 102,135 |
Hy3tencent/hy3 | Tool callingReasoningJSON output | 262,144 | 45,701 | 182,804 |
Hy4tencent/hy4 | Image inputTool callingReasoningJSON output | 1,048,576 | 144,373 | 432,947 |
Hy4 previewtencent/hy4-preview | Tool callingReasoningJSON output | 1,048,576 | 288,747 | 865,895 |
Hy3 previewtencent/hy3-preview | Tool callingReasoning | 262,144 | 62,319 | 207,732 |
Common questions about the Tencent API
- How do I reach the Tencent API from Iran?
- Sign up with your mobile number, top the wallet up in toman and create an sk-up- key. Then, in the official OpenAI SDK, point base_url at https:/
/ api.uttapen.ir/ v1 and set model to the Tencent model id. No international card, no VPN. - What do Tencent models cost in toman?
- It depends on the model: the cheapest, Hy-MT2-1.8B, is about 99 toman for a 1,000-word request, and the dearest, Hy4 preview, about 1,501 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Tencent models are on uttapen?
- 8. 4 support tool calling and 1 accepts image input. The catalogue re-syncs hourly, so a newly released model shows up here on its own.