Hy4 preview
$0.834 per 1M input tokens and $2.50 per 1M output tokens · 1.05M context · tools, reasoning, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What Hy4 preview costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $339 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $86.69 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $146 |
| Content generation 30 long articles a day | $7.88 |
| Classification / extraction 100,000 short items a day | $863 |
Price history
We started tracking Hy4 preview on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run Hy4 preview: 4 providers
DeepInfra is the cheapest at $0.834 input / $2.50 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
| Provider | Input / 1M | Output / 1M | Context | Uptime | Notes |
|---|---|---|---|---|---|
| DeepInfra | $0.834 | $2.50 | 1.05M | 98.4% | fp4 |
| Novita | $0.834 | $2.50 | 1M | 100% | fp8 |
| SiliconFlow | $0.834 | $2.50 | 1.05M | 98.5% | fp8 |
| Tencent | $0.834 | $2.50 | 1.05M | 100% | fp8 |
Cheaper alternatives to Hy4 preview
Models with the same tool calling, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| MiMo-V2.6-Pro Xiaomi | $0.435 | $0.87 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
| GLM 5.3 Z.ai | $0.079 | $1.40 | 1.05M | toolsreasoningJSONopen weights |
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | visiontoolsreasoningJSON |
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
| Ling 3.1 Flash inclusionAI | $0.075 | $0.225 | 262K | toolsreasoningJSON |
How to pay less for Hy4 preview
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $510 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to MiMo-V2.6-Pro (similar capabilities) | $136 | $374 (73%) |
| Use prompt caching (60% of input cached) | $339 | $171 (34%) |
Other workloads: cut-your-bill tool for Hy4 preview.
Specifications
| Model ID | tencent/hy4-preview |
| Input | text |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | Yes |
| Open weights | Yes — tencent/Hy4-preview |
| Released | Aug 28, 2026 |
FAQ
- How much does Hy4 preview cost?
- $0.834 per million input tokens and $2.50 per million output tokens; cached input costs $0.042 per million. Prices as of Oct 21, 2026.
- What is the context window of Hy4 preview?
- 1.05M tokens, with up to 64K output tokens per response.
- Does Hy4 preview support images, tools and structured output?
- Images as input: no. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
- What are cheaper alternatives to Hy4 preview?
- Models with the same key capabilities for at least 20% less include MiMo-V2.6-Pro ($0.435 / $0.87), GLM 5.3 ($0.079 / $1.40), Claude Haiku 5.5 ($0.10 / $0.50).
More from Tencent: all Tencent models · how we collect prices