--- title: Baidu: ERNIE 4.5 VL 28B A3B | Text Generation | ModelsLab description: Lightweight multimodal MoE LLM with 28B total/3B active params, 131K context; excels in visual reasoning, grounding, video understanding & 2-3x faster. url: https://modelslab.com/models/baidu/baidu-ernie-4.5-vl-28b-a3b/api.md canonical: https://modelslab.com/models/baidu/baidu-ernie-4.5-vl-28b-a3b/api.md type: product component: Playground/LLM/Index generated_at: 2026-04-15T02:10:18.220218Z --- Baidu: ERNIE 4.5 VL 28B A3B --- [LLMs.txt](https://modelslab.com/models/open_router/baidu-ernie-4.5-vl-28b-a3b/llms.txt) [.md](https://modelslab.com/models/baidu/baidu-ernie-4.5-vl-28b-a3b.md) baidu-ernie-4.5-vl-28b-a3b baidu Closed Source Model $0.350000 / call Baidu: ERNIE 4.5 VL 28B 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 ### Baidu: ERNIE 4.5 VL 28B A3B baidu baidu-ernie-4.5-vl-28b-a3b Copy model ID PricingInput $0.14 / 1M tokens Output $0.56 / 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) [MM](https://modelslab.com/models/open_router/mistralai-ministral-14b-2512)[Open Router](https://modelslab.com/models/open_router) [Mistral: Ministral 3 14B 2512 Closed Source Model](https://modelslab.com/models/open_router/mistralai-ministral-14b-2512) [MM](https://modelslab.com/models/open_router/mistralai-mixtral-8x7b-instruct)[Open Router](https://modelslab.com/models/open_router) [Mistral: Mixtral 8x7B Instruct Closed Source Model](https://modelslab.com/models/open_router/mistralai-mixtral-8x7b-instruct) [OG](https://modelslab.com/models/open_router/openai-gpt-oss-120b-free)[Open Router](https://modelslab.com/models/open_router) [OpenAI: gpt-oss-120b (free) Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-oss-120b-free) [QQ](https://modelslab.com/models/alibaba_cloud/qwen-qwen3.5-122b-a10b)[Alibaba](https://modelslab.com/models/alibaba_cloud) [Qwen: Qwen3.5-122B-A10B Closed Source Model](https://modelslab.com/models/alibaba_cloud/qwen-qwen3.5-122b-a10b) [XM](https://modelslab.com/models/open_router/xiaomi-mimo-v2-flash)[Open Router](https://modelslab.com/models/open_router) [Xiaomi: MiMo-V2-Flash Closed Source Model](https://modelslab.com/models/open_router/xiaomi-mimo-v2-flash) [OO](https://modelslab.com/models/open_router/openai-o3-mini-high)[Open Router](https://modelslab.com/models/open_router) [OpenAI: o3 Mini High Closed Source Model](https://modelslab.com/models/open_router/openai-o3-mini-high) [Q7](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-7B)[Together AI](https://modelslab.com/models/together_ai) [Qwen2.5 7B Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-7B) [GG](https://modelslab.com/models/open_router/google-gemini-2.5-flash)[Open Router](https://modelslab.com/models/open_router) [Google: Gemini 2.5 Flash Closed Source Model](https://modelslab.com/models/open_router/google-gemini-2.5-flash) [GG](https://modelslab.com/models/open_router/google-gemini-2.0-flash-lite-001)[Open Router](https://modelslab.com/models/open_router) [Google: Gemini 2.0 Flash Lite Closed Source Model](https://modelslab.com/models/open_router/google-gemini-2.0-flash-lite-001) [QQ](https://modelslab.com/models/open_router/qwen-qwen-max)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen-Max Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen-max) [OG](https://modelslab.com/models/open_router/openai-gpt-5.1-codex)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-5.1-Codex Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-5.1-codex) [QV](https://modelslab.com/models/qwen/Qwen-Qwen2.5-VL-72B-Instruct)[ModelsLab](https://modelslab.com/models/qwen) [Qwen2.5-VL (72B) Instruct Closed Source Model](https://modelslab.com/models/qwen/Qwen-Qwen2.5-VL-72B-Instruct) [GG](https://modelslab.com/models/open_router/google-gemma-3-27b-it)[Open Router](https://modelslab.com/models/open_router) [Google: Gemma 3 27B Closed Source Model](https://modelslab.com/models/open_router/google-gemma-3-27b-it) [ML](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo)[Together AI](https://modelslab.com/models/together_ai) [Meta Llama 3.1 8B Instruct Turbo Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo) [Q2](https://modelslab.com/models/together_ai/Qwen-Qwen3-235B-A22B-Instruct-2507-tput)[Together AI](https://modelslab.com/models/together_ai) [Qwen3 235B A22B Instruct 2507 FP8 Throughput Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-235B-A22B-Instruct-2507-tput) [L3](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-70B)[Together AI](https://modelslab.com/models/together_ai) [Llama 3.1 70B Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-70B) [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) [GG](https://modelslab.com/models/open_router/google-gemini-2.5-pro)[Open Router](https://modelslab.com/models/open_router) [Google: Gemini 2.5 Pro Closed Source Model](https://modelslab.com/models/open_router/google-gemini-2.5-pro) About Baidu: ERNIE 4.5 VL 28B A3B --- A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing.... ### Technical Specifications Model IDbaidu-ernie-4.5-vl-28b-a3bCategoryLLM ModelsTaskText GenerationPrice$0.350000 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 Baidu: ERNIE 4.5 VL 28B 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": "baidu-ernie-4.5-vl-28b-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/baidu/baidu-ernie-4.5-vl-28b-a3b/api) for SDKs, code examples in Python, JavaScript, and more. ### Pricing Baidu: ERNIE 4.5 VL 28B A3B API costs $0.350000 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 Baidu](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Baidu: ERNIE 4.5 VL 28B A3B FAQ --- ### What is Baidu: ERNIE 4.5 VL 28B A3B? A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing.... ### How do I use the Baidu: ERNIE 4.5 VL 28B A3B API? You can integrate Baidu: ERNIE 4.5 VL 28B A3B into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "baidu-ernie-4.5-vl-28b-a3b" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Baidu: ERNIE 4.5 VL 28B A3B cost? Baidu: ERNIE 4.5 VL 28B A3B costs $0.350000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Baidu: ERNIE 4.5 VL 28B A3B model ID? The model ID for Baidu: ERNIE 4.5 VL 28B A3B is "baidu-ernie-4.5-vl-28b-a3b". Use this ID in your API requests to specify this model. ### Does Baidu: ERNIE 4.5 VL 28B A3B have a free tier? Yes, ModelsLab offers a free tier that lets you try Baidu: ERNIE 4.5 VL 28B 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*