Models
| Provider | Model | Input | Output | Context |
|---|---|---|---|---|
ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model focused on deeper, higher-quality reasoning. It's tuned to perform strongly on logic, math, science, coding, text generation, and advanced academic benchmarks, delivering top-tier capability with efficient compute usage. BaiduChatOct 8, 2025 | Input$0.035/1M | Output$0.14/1M | Context131K | |
ERNIE 4.0 8K by Baidu. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. BaiduChat | Input$49.72/1M | Output$49.72/1M | Context8K | |
ERNIE Lite 8K 0308 by Baidu. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. BaiduChat | Input$112.50/1M | Output$225.00/1M | Context8K | |
ERNIE Lite 8K 0922 by Baidu. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. BaiduChat | Input$112.50/1M | Output$225.00/1M | Context8K | |
ERNIE Speed 128K by Baidu. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. BaiduChat | Input$1.46/1M | Output$2.92/1M | Context131K | |
ERNIE Speed 8K by Baidu. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. BaiduChat | Input$1.46/1M | Output$2.92/1M | Context8K | |
ERNIE 3.5 8K by Baidu. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. BaiduChat | Input$5.57/1M | Output$5.57/1M | Context8K |