Technical Specifications of hunyuan-all
| Specification | Details |
|---|---|
| Model ID on CometAPI | hunyuan-all |
| Model family | Tencent Hunyuan / Tencent HY multimodal model family |
| Provider | Tencent |
| Model type | General-purpose and multimodal large-model access point |
| Core capabilities | Text generation, multi-round dialogue, reasoning, content creation, and access to broader multimodal Hunyuan capabilities |
| Modalities in Hunyuan family | Text, image, video, and 3D across the broader Tencent Hunyuan ecosystem |
| API style | Chat-completions style invocation is supported in Tencent Hunyuan documentation |
| Notable platform traits | Enterprise-oriented deployment, AI search support with online plug-ins, and Tencent ecosystem integration |
| Best fit | Assistants, knowledge Q&A, business automation, content generation, and multimodal application workflows |
What is hunyuan-all?
hunyuan-all is CometAPI’s platform identifier for accessing Tencent’s Hunyuan model family, a self-developed general-purpose and multimodal large-model suite built for enterprise AI use cases. Tencent describes Hunyuan as covering multiple modalities—including text, image, video, and 3D—and positioning it for scenarios such as content production, knowledge-based question answering, and business automation.
Based on Tencent’s official product and documentation pages, Hunyuan is designed for strong content creation, mathematical and logical reasoning, code-related tasks, and multi-round dialogue. Tencent also documents support for API-based access through chat-completions style calls and highlights AI search with online plug-ins for real-time and deeper content retrieval.
In practice, hunyuan-all is best understood as a convenient aggregator-facing entry for developers who want to route requests to the Hunyuan ecosystem through CometAPI without having to manage Tencent-native integration details directly.
Main features of hunyuan-all
- Multimodal foundation: Tencent positions Hunyuan as a multimodal model family spanning text, image, video, and 3D workloads, making
hunyuan-allrelevant for applications that may expand beyond pure text over time. - Strong text and dialogue performance: Official documentation highlights high-quality content generation, multi-round conversation, and strong task execution, which makes the model suitable for assistants, support bots, and general productivity use cases.
- Reasoning and logic support: Tencent specifically emphasizes mathematical logic and reasoning capabilities in the Hunyuan family, which is useful for analysis, structured answers, and more complex prompt workflows.
- Code and business automation potential: Tencent’s materials mention code generation and enterprise service scenarios, suggesting good fit for internal copilots, workflow automation, and operational knowledge tools.
- AI search and plugin integration: Hunyuan documentation notes support for AI search with online plug-ins, enabling more current and retrieval-augmented application experiences when supported in the deployment stack.
- Enterprise-oriented ecosystem: Tencent presents Hunyuan as an enterprise-grade offering backed by Tencent Cloud infrastructure and broader product ecosystem integration.
How to access and integrate
Step 1: Sign Up for API Key
Sign up on CometAPI and create an API key from the dashboard. After you have your key, store it securely and use it in the Authorization header as a Bearer token for all requests.
Step 2: Send Requests to hunyuan-all API
Use CometAPI’s OpenAI-compatible endpoint and specify hunyuan-all as the model.
curl https://api.cometapi.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $COMETAPI_API_KEY" \
-d '{
"model": "hunyuan-all",
"messages": [
{
"role": "user",
"content": "Write a short introduction to Tencent Hunyuan."
}
]
}'
Python example:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_COMETAPI_KEY",
base_url="https://api.cometapi.com/v1"
)
response = client.chat.completions.create(
model="hunyuan-all",
messages=[
{"role": "user", "content": "Write a short introduction to Tencent Hunyuan."}
]
)
print(response.choices[0].message.content)
Step 3: Retrieve and Verify Results
Read the generated content from the response object, then validate output quality for your use case. For production workloads, you should test prompt consistency, latency, formatting reliability, and factual accuracy using representative inputs before deployment.