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 OpenAI: gpt-oss-120b (exacto)
OpenAI: gpt-oss-120b (exacto) wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimize…
Model details →Side-by-side comparison
| Capability | Baidu: ERNIE 4.5 21B A3B Thinking | OpenAI: gpt-oss-120b (exacto) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 131K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.07 | $0.04 | 🏆 OpenAI: gpt-oss-120b (exacto) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.28 | $0.19 | 🏆 OpenAI: gpt-oss-120b (exacto) |
| Tool / function calling First-class support for emitting structured tool calls. | — | Yes | 🏆 OpenAI: gpt-oss-120b (exacto) |
| 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 OpenAI: gpt-oss-120b (exacto)?
OpenAI: gpt-oss-120b (exacto) wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Baidu: ERNIE 4.5 21B A3B Thinking and OpenAI: gpt-oss-120b (exacto)?
Input: $0.07 vs $0.04 per 1M tokens. Output: $0.28 vs $0.19 per 1M tokens.
What context windows do Baidu: ERNIE 4.5 21B A3B Thinking and OpenAI: gpt-oss-120b (exacto) support?
Baidu: ERNIE 4.5 21B A3B Thinking supports up to 131K tokens. OpenAI: gpt-oss-120b (exacto) supports up to 131K tokens.
Do both Baidu: ERNIE 4.5 21B A3B Thinking and OpenAI: gpt-oss-120b (exacto) support tool calling?
Baidu: ERNIE 4.5 21B A3B Thinking: not advertised. OpenAI: gpt-oss-120b (exacto): yes.