Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that require planning, context continuity, and sustained multi-step execution.
$0.375market price $0.751
$0.0189market price $0.0378
$1.13market price $2.25
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Daily usage of this model on NagaAI.
Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that require planning, context continuity, and sustained multi-step execution.
On NagaAI, Hy4 preview costs $0.375 per 1M input tokens and $1.13 per 1M output tokens. You pay only for what you use, with no subscription.
Hy4 preview reads up to 1.0M tokens in one request, counting the prompt and the answer together.
Yes. Hy4 preview can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Hy3Tencent
Kimi K3.1 ProMoonShotAI
GPT-6.1 TerraOpenAI
MiniMax M3.1 FlashMinimax
Mercury 3Inception
Beam 1.0 501B A23BReflection