One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.834 = $0.834
- Output0.1M x $2.501 = $0.2501
$1.08per session
Tencent - Open weights
Hy4 preview pricing and specs
Hy4 preview is an open-weights model from Tencent that costs $0.834 per 1M input tokens and $2.501 per 1M output tokens on the first-party API, with a 1M-token context window.
Last verified from tencentcloud.com. All sources
- Input / 1M
- $0.834
- Output / 1M
- $2.501
- Context
- 1M tokens
- Weights
- Open
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.834 |
| Output | $2.501 |
| Cache read | $0.042 |
Note: Sold through Tencent Cloud TokenHub (international), Tencent's first-party LLM service. The pricing page has a single 'Cache' column (USD per 1M tokens), recorded as cache read; the launch post calls it the price 'for cache hits'. No separate cache-write, batch or peak/off-peak price is listed for Hy models. The price is the same in both regional language-model tables on the pricing page (Singapore/Guangzhou tabs). The model list gives context as '1M' with max input 960k and max output 64k; the launch post says the context window exceeds 1M tokens. 770B total / 49B active parameters. Release date from the Tencent launch post (published 2026-08-28). Vercel AI Gateway lists it with a 1,024,000 context; the first-party figure is recorded here. It is a preview model.
Specs
- Context window
- 1,000,000 tokens
- Max output
- 64,000 tokens
- Release date
- Provider
- Tencent
- API model id
hy4-preview- Vercel AI Gateway id
tencent/hy4-preview- Weights
- Open weights
- License
- Apache-2.0
- Weights download
- huggingface.co
What Hy4 preview 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 $0.834 = $16.68
- Output5M x $2.501 = $12.51
$29.19per day
$875.55 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.042 = $0.0378
- Uncached input0.1M x $0.834 = $0.0834
- Output0.1M x $2.501 = $0.2501
$0.3713per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Hy4 preview (this page) | $0.834 | $2.501 |
| Amazon Nova 2 LiteAmazon | $0.30 | $2.50 |
| Dola Seed 2.1 TurboByteDance Seed | $0.50 | $2.50 |
| Gemini 2.5 FlashGoogle | $0.30 | $2.50 |
| Gemini 3.5 Flash-LiteGoogle | $0.30 | $2.50 |
| Hy3Tencent | $0.132 | $0.528 |
| Hy-MT2-PlusTencent | $0.074 | $0.295 |
| Hy-MT2-ProTencent | $0.074 | $0.295 |
| Hy-MT2-LiteTencent | $0.044 | $0.177 |
Related reading
- 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 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 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 Hy4 preview cost per million tokens?
Hy4 preview costs $0.834 per 1M input tokens and $2.501 per 1M output tokens on Tencent's first-party API, per tencentcloud.com on October 17, 2026. Per 1M tokens, cache reads cost $0.042.
What is Hy4 preview's context window?
Hy4 preview has a 1,000,000-token context window and returns up to 64,000 output tokens per response.
Are Hy4 preview's weights open?
Yes. Hy4 preview's weights are published at https://huggingface.co/tencent/Hy4-preview under the Apache-2.0.
When was Hy4 preview released?
Tencent released Hy4 preview on August 28, 2026.
Sources
Last verified from tencentcloud.com.
- https://www.tencentcloud.com/document/product/1300/78937
- https://www.tencentcloud.com/document/product/1300/78934
- https://www.tencentcloud.com/document/product/1300/80695
- https://www.tencent.com/tencent-releases-and-open-sources-tencent-hy4-preview/
- https://huggingface.co/tencent/Hy4-preview
- https://ai-gateway.vercel.sh/v1/models
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.