Billing for AI data preparation - Data Transmission Service

This topic describes the billing methods and pricing for the ai data preparation feature of Data Transmission Service (DTS).

Billing

Only pay-as-you-go (post-paid) is supported.

Billable items

RAGFlow knowledge base (basic service and data preparation service)
Built-in model
Enhanced parsing

Pricing

RAGFlow knowledge base

The cost of a RAGFlow knowledge base depends on the number of base services and data preparation services.

Note

Unit: USD/instance/hour.
You receive a 15-day free trial with your first RAGFlow knowledge base purchase.
Costs on the purchase page are rounded. Your bill is calculated using the rates in the following tables.

Region	Base service pricing	Data preparation pricing
China (Hangzhou)	0.25	0.25
China (Shanghai)
China (Qingdao)
China (Beijing)
China (Zhangjiakou)
China (Hohhot)
China (Ulanqab)
China (Shenzhen)
China (Heyuan)
China (Guangzhou)
China (Chengdu)
China (Hong Kong)	0.3773	0.3773
Singapore	0.343	0.343
Malaysia (Kuala Lumpur)	0.2617	0.2617
Indonesia (Jakarta)	0.343	0.343
US (Virginia)	0.2753	0.2753
US (Silicon Valley)	0.2785	0.2785
Germany (Frankfurt)	0.3293	0.3293

Built-in models

Note

The tables below list pricing by model series. Models within the same series that share the same pricing are not listed individually. If a model has multiple pricing variants (for example, different usage modes), each variant is shown as a separate series.

China (Beijing)

Text and vision models (billed per token)

Model series	Input tokens	Input price (USD/1k tokens)	Output price (USD/1k tokens)
`qwen3-vl-flash` series	0 < tokens ≤ 32K	0.0000264	0.000258
	32K < tokens ≤ 128K	0.0000516	0.000516
	128K < tokens ≤ 256K	0.0001032	0.0010308
`qwen3-vl-plus` series	0 < tokens ≤ 32K	0.0001720236	0.00172023
	32K < tokens ≤ 128K	0.0002580348	0.0025803456
	128K < tokens ≤ 256K	0.0005160696	0.0051606912
`qwen-vl-ocr` series	Not applicable	0.0008604	0.0008604
`text-embedding-v4` series	Not applicable	0.0000864	Not applicable

Audio models (billed by duration)

Model series	Price (USD/second)
`fun-asr` series	0.0000384
`qwen3-asr` series	0.0000384

Singapore

Text and vision models (billed per token)

Model series	Input tokens	Input price (USD/1k tokens)	Output price (USD/1k tokens)
`qwen3-vl-flash` series	0 < tokens ≤ 32K	0.00006	0.00048
	32K < tokens ≤ 128K	0.00009	0.00072
	128K < tokens ≤ 256K	0.000144	0.001152
`qwen3-vl-plus` series	0 < tokens ≤ 32K	0.00024	0.00192
	32K < tokens ≤ 128K	0.00036	0.00288
	128K < tokens ≤ 256K	0.00072	0.00576
`qwen-vl-ocr` series	Not applicable	0.000864	0.000864
`text-embedding-v4` series	Not applicable	0.000084	Not applicable

Audio models (billed by duration)

Model series	Price (USD/second)
`fun-asr` series	0.000042
`qwen3-asr` series	0.000042

Enhanced parsing

Pricing for enhanced parsing varies by edition. The Basic edition has a flat rate, while the Standard edition uses tiered pricing based on monthly parsed pages.

Note

Each image document page is processed using a SOTA model that consumes at least 2,000 tokens for data parsing and preparation.

Edition	Monthly parsed pages	Unit price (USD/page)
Basic	-	0.00289
Standard	0–10,000	0.0362
	10,001–100,000	0.0260
	100,001–500,000	0.0217
	500,001–1,000,000	0.0174
	>1,000,000	0.0145