baidu

Baidu: Qianfan-OCR-Fast (free)

by baidu

OpenRouter
Vision Reasoning

Availability

Available 20 of 20 tracked days. Daily snapshots show whether this model was accessible as a free model on OpenRouter.

AprMay
ModelDays202122232425262728293012345678910111213141516171819
Baidu: Qianfan-OCR-Fast (free)20

About

Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR.

Specifications

Context Length 66K
Max Output Tokens 29K
Modality text+image->text
Input image, text
Output text
Supported Parameters frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, seed, stop, temperature, top_p
Content Moderation No

Error Rate

Based on feedback reported by Free LLM Router users. Error rate reflects the percentage of requests that encountered issues such as rate limiting, unavailability, or errors. Learn more.

Loading chart...

Similar Models

More from Baidu

Frequently Asked Questions

Is Baidu: Qianfan-OCR-Fast (free) free to use?

Yes, Baidu: Qianfan-OCR-Fast (free) is completely free to use through OpenRouter. You can access it via the Free LLM Router API at no cost.

What is the context window for Baidu: Qianfan-OCR-Fast (free)?

Baidu: Qianfan-OCR-Fast (free) supports a context window of 66K tokens (65,536 tokens).

What is the maximum output length for Baidu: Qianfan-OCR-Fast (free)?

Baidu: Qianfan-OCR-Fast (free) can generate up to 29K tokens (28,672 tokens) per response.

Does Baidu: Qianfan-OCR-Fast (free) support vision and image inputs?

Yes, Baidu: Qianfan-OCR-Fast (free) supports image inputs, allowing you to analyze and discuss images alongside text.

Does Baidu: Qianfan-OCR-Fast (free) support reasoning?

Yes, Baidu: Qianfan-OCR-Fast (free) supports reasoning capabilities, allowing it to show its step-by-step thought process.