One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.044 = $0.044
- Output0.1M x $0.177 = $0.0177
$0.0617per session
Tencent - Open weights
Hy-MT2-Lite pricing and specs
Hy-MT2-Lite is an open-weights model from Tencent that costs $0.044 per 1M input tokens and $0.177 per 1M output tokens on the first-party API, with a 8K-token context window.
Last verified from tencentcloud.com. All sources
- Input / 1M
- $0.044
- Output / 1M
- $0.177
- Context
- 8K tokens
- Weights
- Open
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.044 |
| Output | $0.177 |
Note: Lightweight translation LLM on Tencent Cloud TokenHub (international). There is no cache price ('-'). Context 8k, max input 4k, max output 4k. The Hy API Guide says Hy-MT2-Lite has '1.8B parameters'. The weights link is the official Hy-MT2-1.8B repo (Apache-2.0), matched by that parameter count. The release date is left blank because no dated Tencent launch post was found.
Specs
- Context window
- 8,000 tokens
- Max output
- 4,000 tokens
- Provider
- Tencent
- API model id
hy-mt2-lite- Vercel AI Gateway id
tencent/hy-mt2-lite- Weights
- Open weights
- License
- Apache-2.0
- Weights download
- huggingface.co
What Hy-MT2-Lite costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.044 = $0.88
- Output5M x $0.177 = $0.885
$1.77per day
$52.95 per 30-day month
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Hy-MT2-Lite (this page) | $0.044 | $0.177 |
| Ministral 3 14BMistral AI | $0.20 | $0.20 |
| Command R7BCohere | $0.0375 | $0.15 |
| Ministral 3 8BMistral AI | $0.15 | $0.15 |
| Amazon Nova MicroAmazon | $0.035 | $0.14 |
| Hy-MT2-PlusTencent | $0.074 | $0.295 |
| Hy-MT2-ProTencent | $0.074 | $0.295 |
| Hy3Tencent | $0.132 | $0.528 |
| Hy4 previewTencent | $0.834 | $2.501 |
Related reading
- Tencent WorkBuddy Explained: Pricing, Free Models, VerdictTencent WorkBuddy is a desktop AI agent for office work running Hy3, DeepSeek and more via TokenHub. What it costs, the free tokens and when to skip it.
- Tencent Hy4 Preview: 770B Open MoE, Agentic Benchmarks, and Where It Fits in 2026Tencent Hy4 preview is a 770B open MoE with 49B active under Apache 2.0. Architecture, posted agentic benchmarks, OpenRouter pricing and self-hosting needs.
- Tencent Hy3: A 295B Open MoE That Punches Above Its WeightTencent's Hy3 ships 295B parameters but activates only 21B per token, matching flagship performance at flash-tier pricing under Apache 2.0.
FAQ
How much does Hy-MT2-Lite cost per million tokens?
Hy-MT2-Lite costs $0.044 per 1M input tokens and $0.177 per 1M output tokens on Tencent's first-party API, per tencentcloud.com on October 17, 2026.
What is Hy-MT2-Lite's context window?
Hy-MT2-Lite has a 8,000-token context window and returns up to 4,000 output tokens per response.
Are Hy-MT2-Lite's weights open?
Yes. Hy-MT2-Lite's weights are published at https://huggingface.co/tencent/Hy-MT2-1.8B under the Apache-2.0.
Sources
Last verified from tencentcloud.com.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.