ERNIE 4.5 VL 28B A3B Thinking
ERNIE 4.5 VL 28B A3B Thinking is Baidu's language model with a 131K context window and up to 66K output tokens, starting at $0.390 / 1M input and $0.390 / 1M output. A reasoning-enhanced multimodal MoE model from Baidu built on ERNIE-4.5-VL-28B-A3B, delivering improved performance on complex visual reasoning tasks.
Capabilities
Input1/5
Text·
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Novita | $0.390 | $0.390 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| ERNIE 5 Thinking Preview | — | — | — | — | Available |
| ERNIE 4.5 21B A3B Thinking | 131K | $0.070 | $0.280 | Available | |
| ERNIE 4.5 300B A47B | 131K | $0.280 | $1.10 | Available | |
| ERNIE 4.5 VL 424B A47B | 131K | $0.420 | $1.25 | Available | |
| ERNIE 4.5 VL 28B A3B Thinking | — | 131K | $0.390 | $0.390 | Current |
| ERNIE 4.5 300B A47B Paddle | — | 123K | $0.280 | $1.10 | Available |