---
title: Baidu: ERNIE 4.5 21B A3B API | Text Generation | ModelsLab
description: Lightweight MoE language model with 21B total/3B active parameters, 131K context window, excels at reasoning, coding, and long-document analysis with.
url: https://modelslab.com/models/baidu/baidu-ernie-4.5-21b-a3b.md
canonical: https://modelslab.com/models/baidu/baidu-ernie-4.5-21b-a3b.md
type: product
component: Playground/LLM/Index
generated_at: 2026-04-15T00:22:46.080528Z
---

Baidu: ERNIE 4.5 21B A3B
---

 [LLMs.txt](https://modelslab.com/models/open_router/baidu-ernie-4.5-21b-a3b/llms.txt) [.md](https://modelslab.com/models/baidu/baidu-ernie-4.5-21b-a3b.md)

baidu-ernie-4.5-21b-a3b baidu Closed Source Model $0.175000 / call

Baidu: ERNIE 4.5 21B 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 21B A3B

baidu baidu-ernie-4.5-21b-a3b

Copy model ID

PricingInput $0.07 / 1M tokens

Output $0.28 / 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)

[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)

[QQ](https://modelslab.com/models/open_router/qwen-qwen3-coder-free)[Open Router](https://modelslab.com/models/open_router)

 [Qwen: Qwen3 Coder 480B A35B (free)

Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-coder-free)

[ML](https://modelslab.com/models/open_router/mistralai-mistral-large-2411)[Open Router](https://modelslab.com/models/open_router)

 [Mistral Large 2411

Closed Source Model](https://modelslab.com/models/open_router/mistralai-mistral-large-2411)

[M(](https://modelslab.com/models/together_ai/mistralai-Mistral-7B-Instruct-v0.1)[Together AI](https://modelslab.com/models/together_ai)

 [Mistral (7B) Instruct v0.1

Closed Source Model](https://modelslab.com/models/together_ai/mistralai-Mistral-7B-Instruct-v0.1)

[AN](https://modelslab.com/models/open_router/amazon-nova-micro-v1)[Open Router](https://modelslab.com/models/open_router)

 [Amazon: Nova Micro 1.0

Closed Source Model](https://modelslab.com/models/open_router/amazon-nova-micro-v1)

[OG](https://modelslab.com/models/open_router/openai-gpt-5.3-codex)[Open Router](https://modelslab.com/models/open_router)

 [OpenAI: GPT-5.3-Codex

Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-5.3-codex)

[ZG](https://modelslab.com/models/open_router/z-ai-glm-5.1)[Open Router](https://modelslab.com/models/open_router)

 [Z.ai: GLM 5.1

Closed Source Model](https://modelslab.com/models/open_router/z-ai-glm-5.1)

[BE](https://modelslab.com/models/open_router/baidu-ernie-4.5-vl-28b-a3b)[Open Router](https://modelslab.com/models/open_router)

 [Baidu: ERNIE 4.5 VL 28B A3B

Closed Source Model](https://modelslab.com/models/open_router/baidu-ernie-4.5-vl-28b-a3b)

[GG](https://modelslab.com/models/open_router/google-gemma-3-4b-it-free)[Open Router](https://modelslab.com/models/open_router)

 [Google: Gemma 3 4B (free)

Closed Source Model](https://modelslab.com/models/open_router/google-gemma-3-4b-it-free)

[XG](https://modelslab.com/models/open_router/x-ai-grok-3-mini)[Open Router](https://modelslab.com/models/open_router)

 [xAI: Grok 3 Mini

Closed Source Model](https://modelslab.com/models/open_router/x-ai-grok-3-mini)

[![Gemini 2.0 Flash](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/f05a6bc4-dd20-49cc-bc2f-8a1c9b25e930.png)](https://modelslab.com/models/google/gemini-2.0-flash-001)[Google](https://modelslab.com/models/google)

 [Gemini 2.0 Flash

Closed Source Model](https://modelslab.com/models/google/gemini-2.0-flash-001)

[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)

[OO](https://modelslab.com/models/open_router/openai-o3-deep-research)[Open Router](https://modelslab.com/models/open_router)

 [OpenAI: o3 Deep Research

Closed Source Model](https://modelslab.com/models/open_router/openai-o3-deep-research)

[OG](https://modelslab.com/models/open_router/openai-gpt-4.1-nano)[Open Router](https://modelslab.com/models/open_router)

 [OpenAI: GPT-4.1 Nano

Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-4.1-nano)

[ZG](https://modelslab.com/models/open_router/z-ai-glm-4.7-flash)[Open Router](https://modelslab.com/models/open_router)

 [Z.ai: GLM 4.7 Flash

Closed Source Model](https://modelslab.com/models/open_router/z-ai-glm-4.7-flash)

[ZG](https://modelslab.com/models/open_router/z-ai-glm-4-32b)[Open Router](https://modelslab.com/models/open_router)

 [Z.ai: GLM 4 32B

Closed Source Model](https://modelslab.com/models/open_router/z-ai-glm-4-32b)

[L2](https://modelslab.com/models/together_ai/LiquidAI-LFM2-24B-A2B)[Together AI](https://modelslab.com/models/together_ai)

 [LFM2-24B-A2B

Closed Source Model](https://modelslab.com/models/together_ai/LiquidAI-LFM2-24B-A2B)

[AJ](https://modelslab.com/models/open_router/ai21-jamba-large-1.7)[Open Router](https://modelslab.com/models/open_router)

 [AI21: Jamba Large 1.7

Closed Source Model](https://modelslab.com/models/open_router/ai21-jamba-large-1.7)

About Baidu: ERNIE 4.5 21B A3B
---

A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an...

### Technical Specifications

Model IDbaidu-ernie-4.5-21b-a3bCategoryLLM ModelsTaskText GenerationPrice$0.175000 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 21B 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

```
<code>import requests
import json

url = "https://modelslab.com/api/v7/llm/chat/completions"

headers = {
    "Content-Type": "application/json"
}

data = {
        "model_id": "baidu-ernie-4.5-21b-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}")</code>
```

View the [full API documentation](https://modelslab.com/models/baidu/baidu-ernie-4.5-21b-a3b/api) for SDKs, code examples in Python, JavaScript, and more.

### Pricing

Baidu: ERNIE 4.5 21B A3B API costs $0.175000 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 21B A3B FAQ
---

### What is Baidu: ERNIE 4.5 21B A3B?

A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an...

### How do I use the Baidu: ERNIE 4.5 21B A3B API?

You can integrate Baidu: ERNIE 4.5 21B 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-4.5-21b-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 21B A3B cost?

Baidu: ERNIE 4.5 21B A3B costs $0.175000 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 21B A3B model ID?

The model ID for Baidu: ERNIE 4.5 21B A3B is "baidu-ernie-4.5-21b-a3b". Use this ID in your API requests to specify this model.

### Does Baidu: ERNIE 4.5 21B A3B have a free tier?

Yes, ModelsLab offers a free tier that lets you try Baidu: ERNIE 4.5 21B 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*