Home / Models / Tencent / Hy-MT2-1.8B

Hy-MT2-1.8B pricing and routing profile

Hy-MT2-1.8B from Tencent lists at $0.044 per million input tokens and $0.177 per million output tokens, with a 8,192-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.044
Output, per 1M tokens$0.177
Context window8K
Confidence signalNot exposed

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.0282
Chat reply (2,000 in, 400 out)$0.159
Retrieval-augmented answer (8,000 in, 500 out)$0.441

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Hy-MT2-1.8B. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Cheaper models that can answer first

Models priced below Hy-MT2-1.8B that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Qwen3.7 Flash$0.03 / $0.1329%
Llama 3 8B Lunaris$0.04 / $0.0537%
Granite 4.0 Micro$0.017 / $0.11250%
gpt-oss-20b$0.018 / $0.0955%
Ling 3.0 Flash$0.021 / $0.06358%
Ling 3.0 Flash VL$0.021 / $0.061658%

Questions

How much does Hy-MT2-1.8B cost?

Hy-MT2-1.8B lists at $0.044 per million input tokens and $0.177 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.159 per 1,000 requests.

What is the context window of Hy-MT2-1.8B?

8,192 tokens.

Can a cheaper model replace Hy-MT2-1.8B?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Hy-MT2-1.8B on one half of your requests and make at most three answers worse on the other.