Hy4 API
Pricing
| Provider | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|
| Novita AI | $0.417 | $0.021 | $1.2505 |
USD, as of November 10, 2026. Live prices
- 1MContext
- 64KMax output
- $0.417/ $1.2505From, per 1M in / out
- 1Provider
Providers
Cost
| Workload | Novita AI |
|---|---|
| 1,000 chat replies2K in, 500 out each | $1.46 |
| 1,000 agent tasks50K in, 5K out each | $27.10 |
| Monthly batch job500M in, 50M out | $271.03 |
Quickstart
curl https://api.routerplus.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tencent/hy4",
"messages": [{ "role": "user", "content": "Hello" }]
}'FAQ
How much does the Hy4 API cost?
On RouterPlus, Hy4 costs $0.417 per million input tokens and $1.2505 per million output tokens at Novita AI, the lowest listed prices and the provider where routing starts. Prices as of November 10, 2026.
Which providers serve Hy4?
Novita AI serves Hy4 on RouterPlus today.
What is the Hy4 model ID?
Use "tencent/hy4" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.
What is the Hy4 context window?
1M tokens of context and up to 64K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.
Is Hy4 open weights?
Yes. Tencent publishes Hy4 as an open-weight model, which is why several independent providers can host it.
Do any Hy4 providers retain prompts?
None of the 1 providers serving Hy4 on RouterPlus list prompt retention.
Can I reserve capacity for Hy4?
Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.