Tencent model
Hy4 API cost calculator
Hy4 costs $0.42 per 1M input tokens and $1.25 per 1M output tokens on the Tencent API, with a 1.0M-token context window. A typical request (2K input, 500 output tokens) costs $0.0015 — about $43.78/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Hy4
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0006 | $0.58 |
| RAG query with context | 4,000 / 500 | $0.0023 | $2.29 |
| Document summarization | 20,000 / 1,000 | $0.0096 | $9.59 |
| Agent coding session | 100,000 / 5,000 | $0.05 | $47.95 |
Hy4 vs other Tencent models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Hy4 | $0.42 | $1.25 | 1.0M |
| Hy4 flash | $0.04 | $0.14 | 1.0M |
| Hy4 preview | $0.83 | $2.50 | 1.0M |
| Hy-MT2-1.8B | $0.04 | $0.18 | 8K |
| Hy-MT2-30B-A3B | $0.07 | $0.29 | 8K |
Frequently asked questions
How much does Hy4 cost per 1M tokens?
According to current pricing data, Hy4 costs $0.42 per 1M input tokens and $1.25 per 1M output tokens. Processing 1M tokens each way costs $1.67.
What does a typical API request to Hy4 cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0015. At 1,000 requests per day that is $1.46 daily, or about $43.78 per month.
What is Hy4's context window?
Hy4 supports a 1.0M-token context window (1,048,576 tokens).
Does Hy4 support prompt caching?
Yes. Cached input tokens cost $0.02 per 1M — a 95% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to Hy4?
GLM 5.2 from Z-ai is currently the cheapest comparable option at $0.01 per 1M input tokens versus $0.42 for Hy4 — roughly 60x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Hy4 vs GLM 5.2 pricing, or run Hy4 head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.