Side-by-side comparison
ERNIE 4.5 VL 28B A3B vs Claude 3 Haiku
Baidu Qianfan
ERNIE 4.5 VL 28B A3B
👁 Vision
🔧 Tools
Input / 1M
$0.1400
Output / 1M
$0.5600
Anthropic
Claude 3 Haiku
👁 Vision
🔧 Tools
Input / 1M
$0.2500
Output / 1M
$1.2500
| ERNIE 4.5 VL 28B A3B | Claude 3 Haiku | |
|---|---|---|
| Provider | Baidu Qianfan | Anthropic |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 30,000 | 200,000 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | vision, tools | vision, tools |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.1400 | 0.2500 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.5600 | 1.2500 |
Frequently asked questions
Which is cheaper, ERNIE 4.5 VL 28B A3B or Claude 3 Haiku?
ERNIE 4.5 VL 28B A3B is cheaper than Claude 3 Haiku on a 50/50 input/output blend by about $0.4 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 VL 28B A3B or Claude 3 Haiku?
Claude 3 Haiku has the larger context window at 200k tokens versus 30k tokens for ERNIE 4.5 VL 28B A3B. That means Claude 3 Haiku can ingest about 6.7x as much text per request.
What is the difference between ERNIE 4.5 VL 28B A3B and Claude 3 Haiku?
ERNIE 4.5 VL 28B A3B comes from Baidu Qianfan; Claude 3 Haiku comes from Anthropic. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.