Side-by-side comparison
ERNIE 4.5 21B A3B vs Hy3 preview
Baidu Qianfan
ERNIE 4.5 21B A3B
🔧 Tools
Input / 1M
$0.0700
Output / 1M
$0.2800
| ERNIE 4.5 21B A3B | Hy3 preview | |
|---|---|---|
| Provider | Baidu Qianfan | Tencent |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 120,000 | 262,144 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | tools | tools |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.0700 | 0.0660 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.2800 | 0.2600 |
Frequently asked questions
Which is cheaper, ERNIE 4.5 21B A3B or Hy3 preview?
Hy3 preview is cheaper than ERNIE 4.5 21B A3B on a 50/50 input/output blend by about $0.012 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, ERNIE 4.5 21B A3B or Hy3 preview?
Hy3 preview has the larger context window at 262k tokens versus 120k tokens for ERNIE 4.5 21B A3B. That means Hy3 preview can ingest about 2.2x as much text per request.
What is the difference between ERNIE 4.5 21B A3B and Hy3 preview?
ERNIE 4.5 21B A3B comes from Baidu Qianfan; Hy3 preview comes from Tencent. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.