--- title: Tongyi DeepResearch 30B A3B | Text Generation | ModelsLab description: Powerful 30B parameter LLM with 3B active params via A3B activation, excels in deep research, text generation, code, and reasoning tasks for advanced NLP. url: https://modelslab.com/models/alibaba/alibaba-tongyi-deepresearch-30b-a3b.md canonical: https://modelslab.com/models/alibaba/alibaba-tongyi-deepresearch-30b-a3b.md type: product component: Playground/LLM/Index generated_at: 2026-04-14T22:32:39.398885Z --- Tongyi DeepResearch 30B A3B --- [LLMs.txt](https://modelslab.com/models/open_router/alibaba-tongyi-deepresearch-30b-a3b/llms.txt) [.md](https://modelslab.com/models/alibaba/alibaba-tongyi-deepresearch-30b-a3b.md) alibaba-tongyi-deepresearch-30b-a3b alibaba Closed Source Model $0.270000 / call Tongyi DeepResearch 30B A3B --- 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 ### Tongyi DeepResearch 30B A3B alibaba alibaba-tongyi-deepresearch-30b-a3b Copy model ID PricingInput $0.09 / 1M tokens Output $0.45 / 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) [DR](https://modelslab.com/models/deepseek/deepseek-ai-DeepSeek-R1-Distill-Llama-70B)[ModelsLab](https://modelslab.com/models/deepseek) [DeepSeek-R1 Closed Source Model](https://modelslab.com/models/deepseek/deepseek-ai-DeepSeek-R1-Distill-Llama-70B) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-8b)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 8B Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-8b) [OG](https://modelslab.com/models/open_router/openai-gpt-5.1-codex-mini)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-5.1-Codex-Mini Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-5.1-codex-mini) [DV](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3.2-Exp)[Together AI](https://modelslab.com/models/together_ai) [Deepseek V3.2 Exp Closed Source Model](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3.2-Exp) [ML](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-70B-Instruct-Turbo)[Together AI](https://modelslab.com/models/together_ai) [Meta Llama 3.1 70B Instruct Turbo Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-70B-Instruct-Turbo) [AN](https://modelslab.com/models/open_router/amazon-nova-2-lite-v1)[Open Router](https://modelslab.com/models/open_router) [Amazon: Nova 2 Lite Closed Source Model](https://modelslab.com/models/open_router/amazon-nova-2-lite-v1) [RF](https://modelslab.com/models/open_router/rekaai-reka-flash-3)[Open Router](https://modelslab.com/models/open_router) [Reka Flash 3 Closed Source Model](https://modelslab.com/models/open_router/rekaai-reka-flash-3) [OG](https://modelslab.com/models/open_router/openai-gpt-4o-2024-05-13)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-4o (2024-05-13) Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-4o-2024-05-13) [G3](https://modelslab.com/models/together_ai/google-gemma-3-1b-it)[Together AI](https://modelslab.com/models/together_ai) [Gemma 3 1b it Closed Source Model](https://modelslab.com/models/together_ai/google-gemma-3-1b-it) [ZG](https://modelslab.com/models/open_router/z-ai-glm-5)[Open Router](https://modelslab.com/models/open_router) [Z.ai: GLM 5 Closed Source Model](https://modelslab.com/models/open_router/z-ai-glm-5) [Q3](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-32B)[Together AI](https://modelslab.com/models/together_ai) [Qwen2.5 32B Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-32B) [DR](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-R1-Original)[Together AI](https://modelslab.com/models/together_ai) [DeepSeek R1 (Original) Closed Source Model](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-R1-Original) [OG](https://modelslab.com/models/open_router/openai-gpt-oss-20b)[Open Router](https://modelslab.com/models/open_router) [OpenAI: gpt-oss-20b Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-oss-20b) [Q9](https://modelslab.com/models/together_ai/Qwen-Qwen3.5-9B)[Together AI](https://modelslab.com/models/together_ai) [Qwen3.5 9B FP8 Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3.5-9B) [NN](https://modelslab.com/models/together_ai/nvidia-NVIDIA-Nemotron-3-Nano-30B-A3B-BF16)[Together AI](https://modelslab.com/models/together_ai) [Nvidia Nemotron 3 Nano 30B A3b Bf16 Closed Source Model](https://modelslab.com/models/together_ai/nvidia-NVIDIA-Nemotron-3-Nano-30B-A3B-BF16) [QC](https://modelslab.com/models/together_ai/Qwen-Qwen3-Coder-Next-FP8)[Together AI](https://modelslab.com/models/together_ai) [Qwen3 Coder Next Fp8 Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-Coder-Next-FP8) [Q7](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-72B)[Together AI](https://modelslab.com/models/together_ai) [Qwen2.5 72B Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-72B) [MM](https://modelslab.com/models/open_router/mistralai-mistral-7b-instruct-v0.1)[Open Router](https://modelslab.com/models/open_router) [Mistral: Mistral 7B Instruct v0.1 Closed Source Model](https://modelslab.com/models/open_router/mistralai-mistral-7b-instruct-v0.1) About Tongyi DeepResearch 30B A3B --- Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks... ### Technical Specifications Model IDalibaba-tongyi-deepresearch-30b-a3bCategoryLLM ModelsTaskText GenerationPrice$0.270000 per million tokensAddedFebruary 20, 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 Tongyi DeepResearch 30B A3B 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": "alibaba-tongyi-deepresearch-30b-a3b", "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}") ``` View the [full API documentation](https://modelslab.com/models/alibaba/alibaba-tongyi-deepresearch-30b-a3b/api) for SDKs, code examples in Python, JavaScript, and more. ### Pricing Tongyi DeepResearch 30B A3B API costs $0.270000 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 Alibaba](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Tongyi DeepResearch 30B A3B FAQ --- ### What is Tongyi DeepResearch 30B A3B? Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks... ### How do I use the Tongyi DeepResearch 30B A3B API? You can integrate Tongyi DeepResearch 30B A3B into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "alibaba-tongyi-deepresearch-30b-a3b" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Tongyi DeepResearch 30B A3B cost? Tongyi DeepResearch 30B A3B costs $0.270000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Tongyi DeepResearch 30B A3B model ID? The model ID for Tongyi DeepResearch 30B A3B is "alibaba-tongyi-deepresearch-30b-a3b". Use this ID in your API requests to specify this model. ### Does Tongyi DeepResearch 30B A3B have a free tier? Yes, ModelsLab offers a free tier that lets you try Tongyi DeepResearch 30B A3B 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 - 2026-04-15*