Author's Description
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 routing....
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Baidu's ERNIE 4.5 VL 28B A3B demonstrates competitive response times, performing in the 55th percentile for speed across various benchmarks. It also offers cost-effective solutions, ranking in the 65th percentile for price. Notably, the model exhibits exceptional reliability with a 100% success rate, consistently providing usable responses without technical failures. In terms of performance across categories, ERNIE 4.5 VL 28B A3B shows a standout strength in Ethics, achieving perfect 100% accuracy, making it the most accurate model at its price point and among models of similar speed. It also performs well in General Knowledge and Email Classification with 96% accuracy in both. However, a notable weakness is observed in its Hallucinations benchmark, where it scores 80% accuracy, indicating some difficulty in acknowledging uncertainty with fictional concepts. Instruction Following (56% accuracy), Coding (82% accuracy), and Reasoning (70% accuracy) show moderate performance. Its innovative heterogeneous MoE structure and RLVR alignment contribute to its strong cross-modal reasoning and generation capabilities, particularly evident in its ethical understanding.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $0.14 |
| Completion | $0.56 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Novita
|
Novita | baidu/ernie-4.5-vl-28b-a3b | 30K | $0.14 / 1M tokens | $0.56 / 1M tokens |
|
Novita
|
Novita | baidu/ernie-4.5-vl-28b-a3b | 30K | $0.14 / 1M tokens | $0.56 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by baidu
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| Baidu: ERNIE 4.5 21B A3B Thinking | Oct 09, 2025 | 21B | 131K |
Text input
Text output
|
★ | ★★ | $$$$ |
| Baidu: ERNIE 4.5 21B A3B | Aug 12, 2025 | 21B | 120K |
Text input
Text output
|
★★★★ | ★★★ | $$ |
| Baidu: ERNIE 4.5 VL 424B A47B | Jun 30, 2025 | 424B | 123K |
Text input
Image input
Text output
|
★★ | ★★★ | $$$$ |
| Baidu: ERNIE 4.5 300B A47B | Jun 30, 2025 | 300B | 123K |
Text input
Text output
|
★ | ★★ | $$$ |