Tencent Hy-MT2-Lite

tencent/hy-mt2-lite

A chat model with a 8K-token context window, at $0.0462 per million input tokens and $0.18585 per million output tokens.

Details

Maker: tencent
Kind: Chat
Context window: 8,000 tokens
Max output: 4,000 tokens
Input: $0.0462 per million tokens
Output: $0.18585 per million tokens
Capabilities: None listed
Takes: Text
Returns: Text
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2026-06-12

Description

Hy-MT2-Lite is Tencent Cloud Hunyuan’s lightweight 1.8B translation model, combining efficient performance with an 8K-token context window and broad multilingual coverage. It supports translation across 33 languages and five ethnic Chinese and dialect variants, delivering strong results on benchmarks including FLORES-200 and WMT25. Designed for professional and real-world business use, it reliably follows instructions for structured, delimiter-preserving, context-aware, glossary-guided, and style-specific translation.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tencent/hy-mt2-lite",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model