Hy4 is the official release of Tencent Hunyuan flagship Mixture-of-Experts model, a major step up from Hy4 Preview with substantial gains in agentic capability and long-horizon, real-world productivity tasks. It is built on a 770B-parameter MoE architecture (about 49B active per token, 78 layers, 256 routed experts plus one shared expert) with a native MTP layer for speculative decoding. It serves a 1M-token context window, accepts text and image input with text output, and generates up to 64K output tokens. Reasoning is configurable at three levels (high / low / none) and defaults to high, so it can run as a deep chain-of-thought model for math, coding, and analysis, or answer directly when latency matters. It supports native tool calling, structured outputs, and the Responses and Anthropic Messages APIs, and is positioned for software engineering, coding agents, office and data analysis, game prototyping, and complex multi-step agent workflows. Tencent recommends temperature 0.9 with top_p 1.0.
OpenAI-compatible — keep the SDK you already use
https://api.orcarouter.ai/v1https://api.orcarouter.aiimport os
from openai import OpenAI
client = OpenAI(
base_url="https://api.orcarouter.ai/v1",
api_key=os.environ["ORCAROUTER_API_KEY"],
)
response = client.chat.completions.create(
model="tencent/hy4",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetools| Input / 1M tokens | $0.834 |
|---|---|
| Output / 1M tokens | $2.501 |
| Cache read / 1M | $0.042 |
| Currency | USD |
Estimate based on list price
Estimate only — actual token counts depend on the provider's tokenizer.
What developers are saying this week
@misc{orcarouter_hy4,
title = {Hy4 API},
author = {Tencent},
year = {2026},
howpublished = {OrcaRouter},
url = {https://www.orcarouter.ai/models/tencent/hy4}
}Tencent. (2026). Hy4 API. OrcaRouter. https://www.orcarouter.ai/models/tencent/hy4