ernie-4.5-21b-a3b-thinking

completions

byopenrouter

ernie-4.5-21b-a3b-thinking

completions

Published by: baiduProvider:

openrouter

ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generation, and expert-level academic benchmarks.

Released

Jun 25, 2025

Knowledge

Dec 27, 2024

License

Proprietary

Context

131072

Input

$0.07 / 1M tokens

Output

$0.28 / 1M tokens

Capabilities: reasoning

Accepts: text

Returns: text

Released Jun 25, 2025Knowledge Cutoff: Dec 27, 2024License: Proprietary

Context: 131072 Input: $0.07 / 1M tokensOutput: $0.28 / 1M tokensCapabilities: reasoningAccepts: textReturns: text

Access ernie-4.5-21b-a3b-thinking through LangDB AI Gateway

Recommended

Integrate with baidu's ernie-4.5-21b-a3b-thinking and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for ernie-4.5-21b-a3b-thinking

Category Performance Scores:

Maths: Score 41.30 (Top 58% - Rank #196)
Finance: Score 28.10 (Top 61% - Rank #206)
Science: Score 71.12 (Top 35% - Rank #118)
Writing: Score 42.27 (Top 63% - Rank #213)
Academia: Score 48.00 (Top 38% - Rank #129)
Marketing: Score 37.37 (Top 73% - Rank #247)
Programming: Score 14.50 (Top 62% - Rank #209)

Overall Performance: 40.37809523809524 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
HLE	3.50	Top 91%	General Knowledge
AIME	49.30	Top 34%	Mathematics
DROP	28.60	Top 81%	General Knowledge
GPQA	81.10	Top 19%	STEM (Physics, Chemistry, Biology)
MMLU	41.90	Top 91%	General Knowledge
SciCode	31.50	Top 49%	Scientific
MATH-500	93.10	Top 34%	Mathematics
MMLU-Pro	77.60	Top 48%	General Knowledge
LiveCodeBench	46.70	Top 49%	Programming
AA Math Index	41.30	Top 58%	Mathematics
AA Coding Index	14.50	Top 62%	Programming
AAII	14.90	Top 64%	General

MMLU Score: 41.90 - Massive Multitask Language Understanding benchmark

GPQA Score: 81.10 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openrouter

Model Type: completions

Context Size: 131072 tokens

Comparing against 337 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

HLE

3.5

General Knowledge

AIME

49.3

Mathematics

DROP

28.6

General Knowledge

GPQA

81.1

STEM (Physics, Chemistry, Biology)

MMLU

41.9

General Knowledge

SciCode

31.5

Scientific

MATH-500

93.1

Mathematics

MMLU-Pro

77.6

General Knowledge

LiveCodeBench

46.7

Programming

AA Math Index

41.3

Mathematics

AA Coding Index

14.5

Programming

AAII

14.9

General

Metric	HLE	AIME	DROP	GPQA	MMLU	SciCode	MATH-500	MMLU-Pro	LiveCodeBench	AA Math Index	AA Coding Index	AAII
Score	3.5	49.3	28.6	81.1	41.9	31.5	93.1	77.6	46.7	41.3	14.5	14.9

Compare with Similar Models

claude-opus-4.5

claude-opus-4.6

gemini-3-flash-preview

claude-sonnet-4.5

gemini-3-pro-preview

claude-sonnet-4

Code Examples

Integration samples and API usage

Code Samples for ernie-4.5-21b-a3b-thinking

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="ernie-4.5-21b-a3b-thinking",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "ernie-4.5-21b-a3b-thinking",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ernie-4.5-21b-a3b-thinking",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: ernie-4.5-21b-a3b-thinking

Provider: openrouter

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from openrouter

ernie-4.5-21b-a3b-thinking

ernie-4.5-21b-a3b-thinking

Access ernie-4.5-21b-a3b-thinking through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

cogito-v2.1-671b

command-a

ernie-4.5-21b-a3b-thinking by openrouter - AI Model Details, Pricing, and Performance Metrics

ernie-4.5-21b-a3b-thinking

ernie-4.5-21b-a3b-thinking

Access ernie-4.5-21b-a3b-thinking through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

cogito-v2.1-671b

command-a