Providers / Tencent Hunyuan / Hunyuan Hy4 Preview
Hunyuan Hy4 Preview API Cost Calculator
Hunyuan Hy4 Preview costs $0.417 per 1M input tokens and $1.2505 per 1M output tokens at official Tencent Hunyuan API prices, verified 2026-11-05. Estimate your own usage below — the calculator is preset to this model.
Calculate your Hunyuan Hy4 Preview cost →Paste text to count tokens instead
Cost per call
—
Estimated monthly cost
—
Official price vs gateway price
| Where | Input / 1M | Output / 1M |
|---|---|---|
| Official API | $0.417 | $1.2505 |
Hunyuan Hy4 Preview is priced above at the official list rate. We have not found a gateway that sells it cheaper with a verifiable public price, so no gateway row is shown — we never estimate one.
Using open-weight models instead (DeepSeek, Qwen, Llama, gpt-oss)? See our Novita AI gateway prices, or go toNovita AI (affiliate).Disclosure.
Preview SKU (hy4-preview). Prefer GA Hunyuan Hy4 (hy4) for new production work unless you need this endpoint.
Introductory 50% TokenHub discount runs through Dec 31, 2026 23:59:59 Beijing time. After that, rates revert to list $0.834 input / $2.501 output / $0.042 cached input per 1M.
Hunyuan Hy4 Preview price facts
| Input | $0.417 per 1M tokens |
|---|---|
| Output | $1.2505 per 1M tokens |
| Cached input | $0.021 per 1M tokens |
| Batch tier | Not published |
| Context window | 1,000,000 tokens |
| Released | 2026-11-04 |
| Price verified | 2026-11-05 · Official source |
What Hunyuan Hy4 Preview costs in practice
| Workload | Per call | Per month |
|---|---|---|
| Chat assistant 2,000 input / 500 output tokens per call, 10,000 calls a month | $0.001459 | $14.59 |
| Document processing 50,000 input / 2,000 output tokens per call, 1,000 calls a month | $0.0234 | $23.35 |
| Agent loop with prompt caching 10,000 fresh input / 100,000 cached input / 2,000 output tokens per call, 500 calls a month | $0.008771 | $4.39 |
Frequently asked questions
How much does Hunyuan Hy4 Preview cost per month?
It depends entirely on token volume. As worked examples: a chat assistant doing 10,000 calls a month costs $14.59, while a document pipeline doing 1,000 long calls costs $23.35. Use the calculator on this page with your own numbers for an exact figure. Prices are official rates verified 2026-11-05.
Is Hunyuan Hy4 Preview cheaper than Hunyuan Hy4?
At a blended workload of 1M input and 250K output tokens, Hunyuan Hy4 Preview costs $0.7296 and Hunyuan Hy4 costs $0.7296 — so Hunyuan Hy4 Preview is the cheaper of the two at this mix. The answer can flip if your workload is mostly output or mostly cached input.
Does Hunyuan Hy4 Preview have batch or caching discounts?
No published batch rate in our sources. Cached input is billed at $0.021 per 1M tokens. Prices verified 2026-11-05. We do not invent unpublished rates.
Are these official prices or gateway prices?
Hunyuan Hy4 Preview on this page uses official Tencent Hunyuan API prices from the provider's public pricing page. Gateway reseller rates, when shown elsewhere on the site, are labeled separately.
Related
Related models
Closest in cost for 1M input + 250K output tokens (standard tier), listed by price.
- Gemini 3.1 Flash-Lite — $0.25 / $1.5 per 1M tokens ($0.625 for that workload)
- GLM-5.3-FlashX — $0.37 / $1.25 per 1M tokens ($0.6825 for that workload)
- GPT-5 Mini — $0.25 / $2 per 1M tokens ($0.75 for that workload)
- GPT-4.1 Mini — $0.4 / $1.6 per 1M tokens ($0.8 for that workload)