--- title: Tencent: Hy3 API | Text Generation | ModelsLab description: Build with Tencent: Hy3 API by Tencent. Text generation, chat, code, and reasoning. Pay-per-use. Free tier. url: https://modelslab.com/models/tencent/tencent-hy3.md canonical: https://modelslab.com/models/tencent/tencent-hy3 type: product component: Playground/LLM/Index generated_at: 2026-07-19T10:02:25.475299Z --- Tencent: Hy3 --- [LLMs.txt](https://modelslab.com/models/tencent/tencent-hy3/llms.txt) [.md](https://modelslab.com/models/tencent/tencent-hy3.md) Tencent: Hy3 --- Choose a prompt below to get started or type your own message Explain quantum computing in simple terms Write a Python function to sort a list Create a marketing email for a SaaS product Compare REST vs GraphQL APIs Send ### Tencent: Hy3 tencent tencent-hy3 Copy model ID PricingInput $0.20 / 1M tokens Output $0.80 / 1M tokens API EndpointsOpenAI Compatible `https://modelslab.com/api/v7/llm/chat/completions`Endpoint Anthropic Compatible `https://modelslab.com/api/v7/llm/v1/messages`Messages `https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens `https://modelslab.com/api/v7/llm/v1/models`Models Use with Claude Code cURL Example ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses. Temperature0.7 Max Tokens1000 Top P0.9 Frequency Penalty0 Presence Penalty0 Model Info Support Related Models --- Discover similar models you might be interested in [View all LLM Models](https://modelslab.com/models?feature=llmaster) [#### Qwen/Qwen3.5 9B FP8 Qwen-Qwen3.5-9B From $0.13/M tokens](https://modelslab.com/models/Qwen/Qwen-Qwen3.5-9B) [#### qwen/Qwen: Qwen3 VL 235B A22B Thinking qwen-qwen3-vl-235b-a22b-thinking From $1.43/M tokens](https://modelslab.com/models/qwen/qwen-qwen3-vl-235b-a22b-thinking) [#### anthropic/Anthropic: Claude 3 Haiku anthropic-claude-3-haiku From $0.75/M tokens](https://modelslab.com/models/anthropic/anthropic-claude-3-haiku) [#### meta/Llama 4 Scout Instruct (17Bx16E) meta-llama-Llama-4-Scout-17B-16E-Instruct From $0.39/M tokens](https://modelslab.com/models/meta/meta-llama-Llama-4-Scout-17B-16E-Instruct) [#### anthropic/Anthropic Claude Sonnet Latest anthropic-claude-sonnet-latest From $6.00/M tokens](https://modelslab.com/models/anthropic/anthropic-claude-sonnet-latest) [#### mistralai/Mistral Large 2407 mistralai-mistral-large-2407 From $4.00/M tokens](https://modelslab.com/models/mistralai/mistralai-mistral-large-2407) [#### mistralai/Mistral (7B) Instruct v0.3 mistralai-Mistral-7B-Instruct-v0.3 From $0.20/M tokens](https://modelslab.com/models/mistralai/mistralai-Mistral-7B-Instruct-v0.3) [#### mistralai/Mistral: Mistral Nemo mistralai-mistral-nemo From $0.02/M tokens](https://modelslab.com/models/mistralai/mistralai-mistral-nemo) [#### byteplus/Seed 1.8 seed-1.8 From $3.00/M tokens](https://modelslab.com/models/byteplus/seed-1.8) [#### anthropic/Anthropic: Claude Opus 4.1 anthropic-claude-opus-4.1 From $45.00/M tokens](https://modelslab.com/models/anthropic/anthropic-claude-opus-4.1) [#### inception/Inception: Mercury 2 inception-mercury-2 From $0.50/M tokens](https://modelslab.com/models/inception/inception-mercury-2) [#### qwen/Qwen: Qwen3 VL 8B Thinking qwen-qwen3-vl-8b-thinking From $0.74/M tokens](https://modelslab.com/models/qwen/qwen-qwen3-vl-8b-thinking) [#### minimax/MiniMax: MiniMax-01 minimax-minimax-01 From $0.65/M tokens](https://modelslab.com/models/minimax/minimax-minimax-01) [#### x-ai/xAI: Grok 4.20 x-ai-grok-4.20 From $1.88/M tokens](https://modelslab.com/models/x-ai/x-ai-grok-4.20) [#### refuel\_ai/Refuel LLM V2 Small togethercomputer-Refuel-Llm-V2-Small From $0.24/M tokens](https://modelslab.com/models/refuel_ai/togethercomputer-Refuel-Llm-V2-Small) [#### qwen/Qwen2-VL (72B) Instruct Qwen-Qwen2-VL-72B-Instruct From $1.20/M tokens](https://modelslab.com/models/qwen/Qwen-Qwen2-VL-72B-Instruct) [#### qwen/Qwen: Qwen3 235B A22B Thinking 2507 qwen-qwen3-235b-a22b-thinking-2507 From $0.82/M tokens](https://modelslab.com/models/qwen/qwen-qwen3-235b-a22b-thinking-2507) [#### google/Gemma 3N E4B Instruct google-gemma-3n-E4B-it From $0.09/M tokens](https://modelslab.com/models/google/google-gemma-3n-E4B-it) Open Source Alternatives --- Explore open-source models that offer similar capabilities with full transparency and flexibility [View all open source models](https://modelslab.com/models?feature=llm&provider=open-source-models) [MU Popular](https://modelslab.com/models/modelslab/uncensored-chat)[ModelsLab](https://modelslab.com/models/modelslab) [Modelslab: Uncensored Chat Open Source Model](https://modelslab.com/models/modelslab/uncensored-chat) About Tencent: Hy3 --- Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:... ### Technical Specifications Model IDtencent-hy3 CategoryLLM Models TaskText Generation Price$0.5 per million tokens AddedJuly 6, 2026 ### Key Features - Chat completion and multi-turn conversation API - Streaming response with token-by-token output - Function calling and tool use support - System prompts and role-based messaging - JSON mode and structured output ### Quick Start Integrate Tencent: Hy3 into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started. PythonJavaScriptcURLPHP ``` import requests import json url = "https://modelslab.com/api/v7/llm/chat/completions" headers = { "Content-Type": "application/json" } data = { "model_id": "tencent-hy3", "messages": [ { "role": "user", "content": "Hello!" } ], "max_tokens": 1000, "key": "YOUR_API_KEY" } try: response = requests.post(url, headers=headers, json=data) response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX) result = response.json() print("API Response:") print(json.dumps(result, indent=2)) except requests.exceptions.HTTPError as http_err: print(f"HTTP error occurred: {http_err} - {response.text}") except Exception as err: print(f"Other error occurred: {err}") ``` ### Pricing Tencent: Hy3 API costs $0.500000 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing) ### Use Cases - AI chatbots and virtual assistants - Code generation and developer tools - Content writing and copywriting automation - Data analysis, summarization, and extraction [Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Tencent](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Tencent: Hy3 FAQ --- ### What is Tencent: Hy3? Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:... ### How do I use the Tencent: Hy3 API? You can integrate Tencent: Hy3 into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "tencent-hy3" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Tencent: Hy3 cost? Tencent: Hy3 costs $0.500000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Tencent: Hy3 model ID? The model ID for Tencent: Hy3 is "tencent-hy3". Use this ID in your API requests to specify this model. ### Does Tencent: Hy3 have a free tier? Yes, ModelsLab offers a free tier that lets you try Tencent: Hy3 and other AI models. Sign up to get free API credits and start building immediately. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-07-19*