Auto-generated comparison

Baidu: ERNIE 4.5 VL 28B A3B vs Qwen: Qwen3 VL 30B A3B Thinking

Qwen: Qwen3 VL 30B A3B Thinking wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.

Side-by-side comparison

CapabilityBaidu: ERNIE 4.5 VL 28B A3BQwen: Qwen3 VL 30B A3B ThinkingWinner
Context window
Maximum number of input tokens the model can attend to in a single request.
30K131K🏆 Qwen: Qwen3 VL 30B A3B Thinking
Input price (per 1M)
Cost per million input tokens billed by the provider.
$0.14$0.13🏆 Qwen: Qwen3 VL 30B A3B Thinking
Output price (per 1M)
Cost per million output tokens billed by the provider.
$0.56$1.56🏆 Baidu: ERNIE 4.5 VL 28B A3B
Tool / function calling
First-class support for emitting structured tool calls.
YesYesTie
Vision input
Accepts image inputs alongside text.
YesYesTie
Reasoning mode
Internal chain-of-thought / extended-thinking support.
YesYesTie

Frequently asked questions

Is Baidu: ERNIE 4.5 VL 28B A3B better than Qwen: Qwen3 VL 30B A3B Thinking?

Qwen: Qwen3 VL 30B A3B Thinking 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 30B A3B Thinking?

Input: $0.14 vs $0.13 per 1M tokens. Output: $0.56 vs $1.56 per 1M tokens.

What context windows do Baidu: ERNIE 4.5 VL 28B A3B and Qwen: Qwen3 VL 30B A3B Thinking support?

Baidu: ERNIE 4.5 VL 28B A3B supports up to 30K tokens. Qwen: Qwen3 VL 30B A3B Thinking supports up to 131K tokens.

Do both Baidu: ERNIE 4.5 VL 28B A3B and Qwen: Qwen3 VL 30B A3B Thinking support tool calling?

Baidu: ERNIE 4.5 VL 28B A3B: yes. Qwen: Qwen3 VL 30B A3B Thinking: yes.

Compare Baidu: ERNIE 4.5 VL 28B A3B with other models

Compare Qwen: Qwen3 VL 30B A3B Thinking with other models