Tencent: Hy4 preview
Hy4 preview is a reasoning model from Tencent released on Aug 28, 2026. It reads text and writes text, with a 1.05M token context window and up to 64K tokens per reply.
Show moreShow less
It costs $0.834 per million input tokens and $2.50 per million output tokens. Cached input bills at $0.042, 95% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
14 providers serve it, including Deep Infra, Hugging Face and Novita AI. The lowest input price is $0.67 per million tokens at Vancine.
- Modalities
- In / out price
- $0.834 / $2.50 per 1M
- Context
- 1.05M
- Max output
- 64K
- Released
- Aug 28, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Hy4 preview pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.834 / 1M tokens | |
|---|---|---|
| Output | $2.50 / 1M tokens | |
| Cached input (read) | $0.042 / 1M tokens | 95% off input |
Hy4 preview providers
14 providers serve it, including Deep Infra, Hugging Face and Novita AI. The lowest input price is $0.67 per million tokens at Vancine. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Deep Infra | $0.834 | $2.50 | $0.042 | 1.05M | 64K |
| Hugging Face | $0.834 | $2.50 | – | 1M | 64K |
| Novita AI | $0.834 | $2.50 | $0.042 | 1M | 64K |
| Vercel AI Gateway | $0.834 | $2.50 | $0.042 | 1.02M | 64K |
| Vancine | $0.67 | $2 | $0.034 | 1.02M | 64K |
| Kilo Gateway | $0.83 | $2.50 | $0.041 | 1.05M | 64K |
| DevPass (LLM Gateway) | $0.834 | $2.50 | $0.042 | 1M | 64K |
| Eden AI | $0.834 | $2.50 | $0.042 | 1.05M | 64K |
| LLM Gateway | $0.834 | $2.50 | $0.042 | 1M | 66K |
| NanoGPT | $0.834 | $2.50 | $0.042 | 1.05M | 64K |
| Tencent TokenHub | $0.834 | $2.50 | $0.042 | 1.02M | 64K |
| AIHubMix | $0.845 | $2.54 | $0.0423 | 1.02M | 64K |
Showing 12 of 14 providers: the lab first, then the major clouds, then the cheapest resellers.
What Hy4 preview costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Hy4 preview through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to Hy4 preview
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- 256K context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 18 providers.
by x-aiApr 16, 2026$1/M input tokens$2/M output tokens18 providers
- Index 33.7
Reads text, images and video. Tool calling, structured output, reasoning. Served by 45 providers.
by qwenAug 14, 2026262K context$0.45/M input tokens$3.20/M output tokens45 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 27 providers.
by googleDec 17, 2025$0.50/M input tokens$3/M output tokens27 providers
- Index 38.4
Reads text and images. Tool calling, structured output, reasoning. Served by 9 providers.
by mistralaiOct 6, 20261.05M context$0.68/M input tokens$2.09/M output tokens9 providers
- Index 22.2
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 24 providers.
by googleJul 9, 20261.05M context$0.30/M input tokens$2.50/M output tokens24 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 32 providers.
by googleMar 20, 2025$0.30/M input tokens$2.50/M output tokens32 providers
More from Tencent
- 8K context
Reads text. Served by 2 providers.
by tencentAug 20, 2026$0.044/M input tokens$0.177/M output tokens2 providers
- 8K context
Reads text. Structured output. Served by 2 providers.
by tencentAug 20, 2026$0.074/M input tokens$0.295/M output tokens2 providers
- 8K context
Reads text. Structured output. Served by 2 providers.
by tencentAug 19, 2026$0.074/M input tokens$0.295/M output tokens2 providers
- Index 25.3
Reads text. Tool calling, structured output, reasoning. Served by 17 providers.
by tencentJul 6, 2026262K context$0.14/M input tokens$0.58/M output tokens17 providers
- 8K context
Reads text.
by tencentJun 12, 2026$0.044/M input tokens$0.177/M output tokens
- 8K context
Reads text. Tool calling. Served by 3 providers.
by tencentMay 21, 2026$0.074/M input tokens$0.295/M output tokens3 providers
Hy4 preview questions
How much does the Hy4 preview API cost?
$0.834 per million input tokens and $2.50 per million output tokens, with cached input at $0.042. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Hy4 preview?
1,048,576 tokens of input, and it can write up to 64,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Hy4 preview?
14 providers serve it, including Deep Infra, Hugging Face and Novita AI. The lowest input price is $0.67 per million tokens at Vancine. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Hy4 preview support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Hy4 preview open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Hy4 preview released?
Aug 28, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. Independent scores from my hand checked rankings, sources linked above. The summary is written from these facts.
Building on Hy4 preview?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting