Hy4 is the official release of Tencent's Hy4 model, succeeding Hy4 Preview, with improvements in agentic capabilities and in long-horizon, real-world productivity tasks. It introduces visual understanding for the first time, accepting text and image input, and supports tool calling, structured outputs and a 1M-token context window.
$0.208
$0.0105
$0.625
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.
Not enough throughput data
Not enough TTFT data
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
Hy4 is the official release of Tencent's Hy4 model, succeeding Hy4 Preview, with improvements in agentic capabilities and in long-horizon, real-world productivity tasks.
On NagaAI, Hy4 costs $0.208 per 1M input tokens and $0.625 per 1M output tokens. You pay only for what you use, with no subscription.
Hy4 reads up to 1.0M tokens in one request, counting the prompt and the answer together.
Yes. Hy4 can call your functions as tools and can answer in a JSON schema you give it.
It takes text and images 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.
Hy4 previewTencentHy3Tencent
Schematron V2 TurboInference.net$0.015 / $0.075 per 1MSchematron V2 SmallInference.net$0.025 / $0.115 per 1M
Qwen3.8 Max PrimeQwen$2 / $6 per 1MParticle-1Particle AI$0.025 / $0.25 per 1MNot enough activity data to display a chart