Tencent model
Hy3 API cost calculator
Hy3 costs $0.08 per 1M input tokens and $0.33 per 1M output tokens on the Tencent API, with a 262K-token context window. A typical request (2K input, 500 output tokens) costs $0.0003 — about $9.90/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 Hy3
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0001 | $0.14 |
| RAG query with context | 4,000 / 500 | $0.0005 | $0.49 |
| Document summarization | 20,000 / 1,000 | $0.0020 | $1.98 |
| Agent coding session | 100,000 / 5,000 | $0.0099 | $9.90 |
Hy3 vs other Tencent models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Hy3 | $0.08 | $0.33 | 262K |
| Hy4 preview | $0.75 | $2.25 | 1.0M |
| Hy-MT2-1.8B | $0.04 | $0.18 | 8K |
| Hy-MT2-30B-A3B | $0.07 | $0.29 | 8K |
| Hy-MT2-7B | $0.07 | $0.29 | 8K |
Frequently asked questions
How much does Hy3 cost per 1M tokens?
According to current pricing data, Hy3 costs $0.08 per 1M input tokens and $0.33 per 1M output tokens. Processing 1M tokens each way costs $0.41.
What does a typical API request to Hy3 cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0003. At 1,000 requests per day that is $0.33 daily, or about $9.90 per month.
What is Hy3's context window?
Hy3 supports a 262K-token context window (262,144 tokens).
Does Hy3 support prompt caching?
Yes. Cached input tokens cost $0.02 per 1M — a 75% 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 Hy3?
DeepSeek Flash Latest from ~deepseek is currently the cheapest comparable option at $0.00 per 1M input tokens versus $0.08 for Hy3 — roughly 825x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Hy3 vs DeepSeek Flash Latest pricing, or run Hy3 head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.