A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated r…
Model details →Baidu: ERNIE 4.5 VL 28B A3B vs Qwen: Qwen3 VL 235B A22B Thinking
Baidu: ERNIE 4.5 VL 28B A3B wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust…
Model details →Side-by-side comparison
| Capability | Baidu: ERNIE 4.5 VL 28B A3B | Qwen: Qwen3 VL 235B A22B Thinking | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 30K | 131K | 🏆 Qwen: Qwen3 VL 235B A22B Thinking |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.14 | $0.26 | 🏆 Baidu: ERNIE 4.5 VL 28B A3B |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.56 | $2.60 | 🏆 Baidu: ERNIE 4.5 VL 28B A3B |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | Yes | Yes | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is Baidu: ERNIE 4.5 VL 28B A3B better than Qwen: Qwen3 VL 235B A22B Thinking?
Baidu: ERNIE 4.5 VL 28B A3B wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Baidu: ERNIE 4.5 VL 28B A3B and Qwen: Qwen3 VL 235B A22B Thinking?
Input: $0.14 vs $0.26 per 1M tokens. Output: $0.56 vs $2.60 per 1M tokens.
What context windows do Baidu: ERNIE 4.5 VL 28B A3B and Qwen: Qwen3 VL 235B A22B Thinking support?
Baidu: ERNIE 4.5 VL 28B A3B supports up to 30K tokens. Qwen: Qwen3 VL 235B A22B Thinking supports up to 131K tokens.
Do both Baidu: ERNIE 4.5 VL 28B A3B and Qwen: Qwen3 VL 235B A22B Thinking support tool calling?
Baidu: ERNIE 4.5 VL 28B A3B: yes. Qwen: Qwen3 VL 235B A22B Thinking: yes.