Side-by-side comparison
Qianfan-OCR-Fast (free) vs Lyria 3 Clip Preview
Baidu Qianfan
Qianfan-OCR-Fast (free)
👁 Vision
Input / 1M
$0.0000
Output / 1M
$0.0000
Google
Lyria 3 Clip Preview
👁 Vision
{} JSON
Input / 1M
$0.0000
Output / 1M
$0.0000
| Qianfan-OCR-Fast (free) | Lyria 3 Clip Preview | |
|---|---|---|
| Provider | Baidu Qianfan | |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 65,536 | 1,048,576 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | vision | vision, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.0000 | 0.0000 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.0000 | 0.0000 |
Frequently asked questions
Which is cheaper, Qianfan-OCR-Fast (free) or Lyria 3 Clip Preview?
Qianfan-OCR-Fast (free) is cheaper than Lyria 3 Clip Preview on a 50/50 input/output blend by about $0 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, Qianfan-OCR-Fast (free) or Lyria 3 Clip Preview?
Lyria 3 Clip Preview has the larger context window at 1M tokens versus 66k tokens for Qianfan-OCR-Fast (free). That means Lyria 3 Clip Preview can ingest about 16.0x as much text per request.
What is the difference between Qianfan-OCR-Fast (free) and Lyria 3 Clip Preview?
Qianfan-OCR-Fast (free) comes from Baidu Qianfan; Lyria 3 Clip Preview comes from Google. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.