Context Window
65,536
Input tokens
Full-context input ≈ $0.04
Model Cost Profile
Developer: baidu· Tokenizer: Other
Canonical ID: baidu/qianfan-ocr-fast-20260420
Pricing updated May 15, 2026
Baidu's Qianfan-OCR-Fast is designed for high-volume document processing, making it ideal for enterprises that require efficient optical character recognition in applications like invoice scanning and automated data entry. With a context window of 65,536 tokens, this model can handle extensive text inputs, allowing for comprehensive analysis and extraction from large documents. Teams utilizing the API should consider the pricing structure, which includes an input cost of $0.68 per million tokens and an output cost of $2.81 per million tokens, to effectively budget for their OCR needs.
Context Window
65,536
Input tokens
Full-context input ≈ $0.04
Max Output
28,672
Completion tokens
Input Price / 1M
$0.6800
Prompt tokens
Output Price / 1M
$2.81
Completion tokens
Top Benchmark
Pending
No benchmark data yet
Price History
Not enough data yet. Price tracking started recently — check back in a few days.
Performance History
Not enough data yet. Performance tracking started recently — check back in a few days.
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.6800 |
| Output (Completion) | $2.81 |
Estimate monthly spend for Baidu: Qianfan-OCR-Fast based on your workload.
Estimated Monthly Cost
$51
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.