Baidu: ERNIE 4.5 300B A47B

This model is no longer available.

Add AI to your application with Puter.js.

Explore Other Models

Model Card

ERNIE 4.5 300B A47B is Baidu's flagship text-only large language model featuring 300B total parameters with 47B active per token via MoE architecture. It demonstrates state-of-the-art performance on instruction following and knowledge benchmarks like IFEval, SimpleQA, and ChineseSimpleQA. The model supports 131K context length and excels at text understanding, generation, reasoning, and coding.

Context Window 131K

tokens

Max Output 12K

tokens

Input Cost $0.28

per million tokens

Output Cost $1.1

per million tokens

Release Date Jun 30, 2025

 

Output Speed 23

tokens / sec

Latency 2.33s

time to first token

Code Example

Add AI to your app with the Puter.js AI API — no API keys or setup required.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms").then(response => {
    document.body.innerHTML = response.message.content;
});

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms").then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

More AI Models From Baidu

Find other Baidu models →

Chat

ERNIE 4.5 VL 28B A3B

ERNIE 4.5 VL 28B A3B is a lightweight multimodal vision-language model with 28B total parameters but only 3B active per token. It processes both images and text simultaneously, enabling tasks like image comprehension, chart analysis, document understanding, and cross-modal reasoning. The model offers both thinking and non-thinking modes while matching performance of larger models like Qwen2.5-VL-32B.

 Chat

ERNIE 4.5 VL 424B A47B

ERNIE 4.5 VL 424B A47B is Baidu's largest multimodal vision-language model with 424B total parameters and 47B active per token. It supports up to 131K context tokens and excels at visual reasoning, document/chart understanding, and visual question answering with both thinking and non-thinking modes. In thinking mode, it approaches or surpasses OpenAI o1 on reasoning benchmarks like MathVista, MMMU, and VisualPuzzle.

Frequently Asked Questions

How do I use ERNIE 4.5 300B A47B?

You can access ERNIE 4.5 300B A47B by Baidu through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is ERNIE 4.5 300B A47B free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add ERNIE 4.5 300B A47B to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for ERNIE 4.5 300B A47B?
ERNIE 4.5 300B A47B costs $0.28 per 1M input tokens and $1.1 per 1M output tokens.
Price per 1M tokens
Input$0.28
Output$1.1
Who created ERNIE 4.5 300B A47B?

ERNIE 4.5 300B A47B was created by Baidu and released on Jun 30, 2025.

What is the context window of ERNIE 4.5 300B A47B?

ERNIE 4.5 300B A47B supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.

What is the max output length of ERNIE 4.5 300B A47B?

ERNIE 4.5 300B A47B can generate up to 12K tokens in a single response.

How does ERNIE 4.5 300B A47B perform on benchmarks?

ERNIE 4.5 300B A47B scores 15.0 on the Artificial Analysis Intelligence Index, outperforming 35% of tracked models. On coding, it scores 14.5 (outperforms 38% of models). On math, it scores 41.3 (outperforms 42% of models).

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the ERNIE 4.5 300B A47B API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add AI to your application without worrying about API keys or setup.

Explore Models View Tutorials