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.
Model details →Baidu: ERNIE 4.5 21B A3B Thinking vs DeepSeek: DeepSeek V3.1
Baidu: ERNIE 4.5 21B A3B Thinking and DeepSeek: DeepSeek V3.1 are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Model details →Side-by-side comparison
| Capability | Baidu: ERNIE 4.5 21B A3B Thinking | DeepSeek: DeepSeek V3.1 | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 164K | 🏆 DeepSeek: DeepSeek V3.1 |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.07 | $0.25 | 🏆 Baidu: ERNIE 4.5 21B A3B Thinking |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.28 | $0.95 | 🏆 Baidu: ERNIE 4.5 21B A3B Thinking |
| Tool / function calling First-class support for emitting structured tool calls. | — | Yes | 🏆 DeepSeek: DeepSeek V3.1 |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is Baidu: ERNIE 4.5 21B A3B Thinking better than DeepSeek: DeepSeek V3.1?
Baidu: ERNIE 4.5 21B A3B Thinking and DeepSeek: DeepSeek V3.1 are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
What's the price difference between Baidu: ERNIE 4.5 21B A3B Thinking and DeepSeek: DeepSeek V3.1?
Input: $0.07 vs $0.25 per 1M tokens. Output: $0.28 vs $0.95 per 1M tokens.
What context windows do Baidu: ERNIE 4.5 21B A3B Thinking and DeepSeek: DeepSeek V3.1 support?
Baidu: ERNIE 4.5 21B A3B Thinking supports up to 131K tokens. DeepSeek: DeepSeek V3.1 supports up to 164K tokens.
Do both Baidu: ERNIE 4.5 21B A3B Thinking and DeepSeek: DeepSeek V3.1 support tool calling?
Baidu: ERNIE 4.5 21B A3B Thinking: not advertised. DeepSeek: DeepSeek V3.1: yes.