---
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-frontend-v2-927501783998.us-east4.run.app/models/baidu/baidu-ernie-4.5-21b-a3b/api.md
canonical: https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/baidu/baidu-ernie-4.5-21b-a3b/api.md
type: product
component: Playground/LLM/Index
generated_at: 2026-05-13T10:36:51.854949Z
---

Baidu: ERNIE 4.5 21B A3B
---

 [LLMs.txt](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/baidu-ernie-4.5-21b-a3b/llms.txt) [.md](https://modelslab-frontend-v2-927501783998.us-east4.run.app/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-frontend-v2-927501783998.us-east4.run.app/models?feature=llmaster)

[ML](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/meta-llama-llama-3.3-70b-instruct)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Meta: Llama 3.3 70B Instruct

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/meta-llama-llama-3.3-70b-instruct)

[DR](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/deepseek/deepseek-ai-DeepSeek-R1-Distill-Qwen-14B)[ModelsLab](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/deepseek)

 [DeepSeek R1 Distill Qwen 14B

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/deepseek/deepseek-ai-DeepSeek-R1-Distill-Qwen-14B)

[ML](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Meta Llama 3.1 8B Instruct Turbo

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo)

[ML](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Meta-Llama-3-70B-Instruct-Turbo)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Meta Llama 3 70B Instruct Turbo

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Meta-Llama-3-70B-Instruct-Turbo)

[MM](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/mistralai-mistral-nemo)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Mistral: Mistral Nemo

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/mistralai-mistral-nemo)

[ZG](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/z-ai-glm-4.5-air-free)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Z.ai: GLM 4.5 Air (free)

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/z-ai-glm-4.5-air-free)

[OO](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-o3)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [OpenAI: o3

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-o3)

[ML](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/meta/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo)[ModelsLab](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/meta)

 [Meta Llama 3.1 8B Instruct Turbo

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/meta/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo)

[L4](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Llama-4-Maverick-17B-128E-Instruct-FP8)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Llama 4 Maverick Instruct (17Bx128E) FP8

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Llama-4-Maverick-17B-128E-Instruct-FP8)

[AC](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/anthropic-claude-opus-4.1)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Anthropic: Claude Opus 4.1

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/anthropic-claude-opus-4.1)

[QQ](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/qwen-qwen3-next-80b-a3b-thinking)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Qwen: Qwen3 Next 80B A3B Thinking

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/qwen-qwen3-next-80b-a3b-thinking)

[SM](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/sarvamai-sarvam-m)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Sarvam M

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/sarvamai-sarvam-m)

[QQ](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/qwen-qwen3.5-35b-a3b)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Qwen: Qwen3.5-35B-A3B

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/qwen-qwen3.5-35b-a3b)

[NN](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/nvidia-NVIDIA-Nemotron-3-Super-120B-A12B-FP8)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Nvidia Nemotron 3 Super 120B A12b Fp8

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/nvidia-NVIDIA-Nemotron-3-Super-120B-A12B-FP8)

[QV](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen3-VL-8B-Instruct)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Qwen3-VL-8B-Instruct

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen3-VL-8B-Instruct)

[N8](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/nim-mistralai-mixtral-8x22b-instruct-v01)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [nim/mistralai/mixtral-8x22b-instruct-v01

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/nim-mistralai-mixtral-8x22b-instruct-v01)

[CC](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/cohere-command-r-plus-08-2024)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Cohere: Command R+ (08-2024)

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/cohere-command-r-plus-08-2024)

[L3](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Meta-Llama-3.1-70B)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Llama 3.1 70B

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Meta-Llama-3.1-70B)

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-frontend-v2-927501783998.us-east4.run.app/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-frontend-v2-927501783998.us-east4.run.app/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-frontend-v2-927501783998.us-east4.run.app/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-frontend-v2-927501783998.us-east4.run.app/models?feature=llmaster) [More from Baidu](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [View Pricing](https://modelslab-frontend-v2-927501783998.us-east4.run.app/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 - 2026-05-13*