Model Cost Profile

Baidu: ERNIE 4.5 21B A3B

Developer: baidu

Pricing updated Mar 11, 2026

Input rank: #65Output rank: #79

Live Pricing

Input: $0.0700

Output: $0.2800

Pricing via OpenRouter API ยท Last synced Mar 11, 2026

Baidu's ERNIE 4.5 21B A3B model offers a robust context window of 120,000 tokens, making it suitable for applications requiring extensive document analysis or long-form content generation. With an input price of $0.07 per 1 million tokens and an output price of $0.28 per 1 million tokens, teams can effectively manage costs while leveraging the model for tasks such as natural language understanding and complex dialogue systems. This model is particularly beneficial for enterprises needing scalable solutions for data-rich environments, where high token capacity enhances performance and user experience.

๐Ÿ”ง Tool Calling

Context Window

120,000

Tokens

Input Price / 1M

$0.0700

Prompt tokens

Output Price / 1M

$0.2800

Completion tokens

Intelligence (MMLU)

Benchmark Pending

Massive Multitask Language Understanding

Price History

Baidu: ERNIE 4.5 21B A3B Pricing Trend

Input / 1M tokens0.0%Output / 1M tokens0.0%
Mar 7 โ€” Mar 11
$0.0700$0.1750$0.2800Mar 7Mar 8Mar 9Mar 10Mar 11

Current Input / 1M

$0.0700

Current Output / 1M

$0.2800

Cheaper Alternatives to Compare

Quick links for cost-down decisions before production rollout.

FAQ

Common pricing and benchmark questions for Baidu: ERNIE 4.5 21B A3B.

How much does Baidu: ERNIE 4.5 21B A3B cost per 1M input tokens?

Baidu: ERNIE 4.5 21B A3B input pricing is $0.0700 per 1M tokens based on the latest synced provider data.

How much does Baidu: ERNIE 4.5 21B A3B cost per 1M output tokens?

Baidu: ERNIE 4.5 21B A3B output pricing is $0.2800 per 1M tokens based on the latest synced provider data.

What context window does Baidu: ERNIE 4.5 21B A3B support?

Baidu: ERNIE 4.5 21B A3B supports a context window of 120,000 tokens.

How can I compare Baidu: ERNIE 4.5 21B A3B with cheaper alternatives?

Use the comparison links on this page to open direct model-vs-model pricing and benchmark pages, then evaluate monthly spend projections for your workload.