Benchable
Text input
Text output
Author's Description
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.
Key Specifications
Supported Parameters
This model supports the following parameters:
Seed
Max Tokens
Logit Bias
Top P
Presence Penalty
Reasoning
Frequency Penalty
Min P
Temperature
Include Reasoning
Stop
Features
This model supports the following features:
Reasoning
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $0.07 |
| Completion | $0.28 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Novita
|
Novita | baidu/ernie-4.5-21b-a3b-thinking | 131K | $0.07 / 1M tokens | $0.28 / 1M tokens |
No benchmark execution results are available for this model yet.
Other Models by baidu
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| Baidu: ERNIE 4.5 21B A3B | Aug 12, 2025 | 21B | 120K |
Text input
Text output
|
★★★★ | ★★★ | $$ |
| Baidu: ERNIE 4.5 VL 28B A3B | Aug 12, 2025 | 28B | 30K |
Image input
Text input
Text output
|
★★★ | ★★★ | $$$ |
| Baidu: ERNIE 4.5 VL 424B A47B | Jun 30, 2025 | 424B | 123K |
Image input
Text input
Text output
|
★★ | ★★★★ | $$$$ |
| Baidu: ERNIE 4.5 300B A47B | Jun 30, 2025 | 300B | 123K |
Text input
Text output
|
★ | ★★ | $$$$ |