Using Hy-MT2 1.8B on Vercel AI Gateway
Implementation guide · Hy-MT2 · Tencent AI Lab
Serverless
Open SourceVercel AI Gateway exposes Hy-MT2 1.8B through model ID tencent/hy-mt2-lite. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the Vercel AI Gateway SDK or REST API to call
tencent/hy-mt2-lite— see the documentation for request format. - 3
Code Examples
Install
pip install openaiAPI key
AI_GATEWAY_API_KEYModel ID
tencent/hy-mt2-litecreator/model-name e.g. kwaipilot/kat-coder-pro-v2
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="tencent/hy-mt2-lite",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Vercel AI Gateway
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.04 |
| Output tokens | $0.18 |
Capabilities
No model capability flags are currently sourced.
About Hy-MT2 1.8B
Tencent Hy-MT2 multilingual translation model (1.8B). Open weights Apache-2.0 on HF. Tencent's own USD per-token price was not available at research time, so the first-party listing has no USD token price.
Model Specs
Released2026-05-11
Parameters1.8B
Context8K
ArchitectureDecoder Only