Last refreshed 2026-10-19. Next refresh: weekly.
Why use Hy-MT2 1.8B on Vercel AI Gateway?
Vercel AI Gateway offers Hy-MT2 1.8B with pay-as-you-go pricing at $0.04/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Hy-MT2 1.8B across 3 providers to find the best fit for your use caseInput / 1M
$0.044
Output / 1M
$0.177
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export AI_GATEWAY_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],Model ID
tencent/hy-mt2-liteRequest example
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)Gotchas
- Use provider model ID "tencent/hy-mt2-lite", not the LLMReference slug "hy-mt2-1.8b".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Hy-MT2 1.8B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Tencent Cloud TI Platform | — | — |
| OpenRouter | $0.04 | $0.18 |
| Vercel AI Gateway | $0.04 | $0.18 |
Pricing
| 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.
Get Started
Model Specs
Released2026-05-11
Parameters1.8B
Context8K
ArchitectureDecoder Only