Baidu: ERNIE 4.5 21B A3B Thinking
Baidu's ERNIE 4.5 21B A3B Thinking has no benchmark data available, and while it is priced very competitively, capability cannot be objectively assessed; without performance evidence it cannot be recommended for professional business use.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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.
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
| Parameters | 21B |
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.07 | $0.000070 |
| Output | $0.28 | $0.000280 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
