Match your billing period and features to your AI reports, image generation and tool usage.
How do monthly and annual billing differ?
Monthly billing renews automatically through Alipay; you can cancel renewal anytime. Annual billing is a single payment with no automatic renewal and a lower yearly cost for the same tier. Annual credits arrive in 12 allocations, not all at once.
What can I use credits for?
Credits pay for model and tool calls, including image generation, research and reports. Rates vary by service; see the price table below. Image and report estimates each assume the full period’s credits and cannot be added together.
What happens when credits run out or remain unused?
Check your balance and buy credit packs in the console when you need more usage. Credit packs require a previous plan purchase. Plan credits are valid for the current period only; unused credits do not roll over.
How Credits Are Used
Credits cover built-in media and speech services, plus App calls beyond the monthly allowance.
Service usage is deducted from credits by unit.
Price reference, updated Nov 13, 2026. Actual charges may vary by usage details.
AIsa
Price (Credits)
300 / USD 1 of provider charges
AIsa API usage.
Aura SR
Price (Credits)
0.24 / second
Upscale images with Aura SR, billed by inference time.
CosyVoice Text to Speech
Price (Credits)
CosyVoice 3.5 Flash: 28.8 / 10k chars
CosyVoice 3.5 Flash: 28.8 / 10k chars
CosyVoice 3 Flash: 36 / 10k chars
CosyVoice 3.5 Plus: 54 / 10k chars
CosyVoice 3 Plus or 2: 72 / 10k chars
Generate multilingual speech with CosyVoice models.
Doubao Seedream
Price (Credits)
Flash output: 4.32 / image
Flash output: 4.32 / image
Pro output (≤2.61 MP): 10.8 / image
Pro output (>2.61 MP): 21.6 / image
Pro layer (≤2.61 MP): 5.4 / image
Pro layer (>2.61 MP): 10.8 / image
Pro extra reference (from the second image): 0.72 / image
Generate, edit and split images into layers with Doubao Seedream.
Doubao Speech to Text
Price (Credits)
68 / hour
Transcribe speech audio into text.
Doubao Text to Speech
Price (Credits)
154 / 10k chars
Generate speech audio from text with Doubao voices.
GPT Image 2 / 2.5
Price (Credits)
1K / 2K: 8 / image
1K / 2K: 8 / image
4K: 20 / image
Generate and edit images with GPT Image 2 and 2.5.
iLovePDF
Price (Credits)
10,400 / 10,000 provider credit
Merge, split, compress, and rotate PDFs, or convert between PDFs and images.
Investoday
Price (Credits)
1 / point
Investoday API usage.
JEV
Price (Credits)
20 / 1M tokens
JEV input token usage.
Jina Reader
Price (Credits)
Read: 10 / 1M tokens
Read: 10 / 1M tokens
Search: 10 / 1M tokens
Read web pages and search web content for agents.
JustOneAPI
Price (Credits)
60 / CNY 1 of provider charges
JustOneAPI API usage.
Kalodata
Price (Credits)
40 / provider credit
Kalodata API usage.
Keepa
Price (Credits)
260 / 1,000 provider token
Keepa API usage.
Kling AI Video
Price (Credits)
Kling 3.0 or Omni 720p without Native Audio or Video Input: 20.8 / second
Kling 3.0 or Omni 720p without Native Audio or Video Input: 20.8 / second
Kling 3.0 or Omni 1080p without Native Audio or Video Input, or Turbo 720p: ~27.8 / second
Kling 3.0 or Omni 720p with Native Audio or Video Input: 31.2 / second
Kling 3.0 Turbo 1080p: ~34.6 / second
Kling 3.0 or Omni 1080p with Native Audio or Video Input: 41.6 / second
Kling 3.0 or Omni 4K: 104 / second
Generate videos with Kling AI 3.0 models from prompts and reference media.
Kuaidi100 Logistics Tracking
Price (Credits)
1.4 / request
Track shipments and retrieve real-time logistics updates with Kuaidi100.
LinkFox
Price (Credits)
0.6 / compute credit
LinkFox API usage.
MiniMax H3
Price (Credits)
768P input and output video: 14.4 / second
768P input and output video: 14.4 / second
2K input and output video: 23.4 / second
Reference images after the first five: 7.2 / image
Generate videos with MiniMax H3. Input and output video seconds are billed; the first five reference images and input audio are free.
Nano Banana
Price (Credits)
Nano Banana: 9.4 / image
Nano Banana: 9.4 / image
Nano Banana Edit: 9.4 / image
Nano Banana Pro 1K or 2K: 36 / image
Nano Banana Pro 4K: 72 / image
Nano Banana 2 0.5K: 14.4 / image
Nano Banana 2 1K: 19.2 / image
Nano Banana 2 2K: 28.8 / image
Nano Banana 2 4K: 38.4 / image
Generate and edit images with Nano Banana models.
OOMOL Copy Proofreader
Price (Credits)
60 / image
Recognize text in images and detect and correct typos in packaging, posters, and other visual copy.
OOMOL RAG
Price (Credits)
Document indexing: 100 / 1M tokens
Document indexing: 100 / 1M tokens
Query embedding: 100 / 1M tokens
Reranking (enabled by default): 100 / 1M tokens
Document indexing, query embedding and optional reranking are charged separately by actual tokens. Reranking is enabled by default.
Open Flow Run
Price (Credits)
0.96 / 30 computationSecond
Run Open Flow workflows across apps and services. Waiting time is excluded. Each billable run is rounded up to 30-second blocks, with a 30-second minimum.
Qwen Audio Text to Speech
Price (Credits)
Qwen-Audio 3.0 Flash: 36 / 10k chars
Qwen-Audio 3.0 Flash: 36 / 10k chars
Qwen-Audio 3.0 / 3.1 Plus: 50.4 / 10k chars
Generate speech with Qwen Audio 3.0 and 3.1 models.
Qwen Custom Voices
Price (Credits)
Voice Cloning: 0.36 / voice
Voice Cloning: 0.36 / voice
Voice Design: 7 / voice
Qwen-Audio 3.0 Flash: 36 / 10k chars
Qwen-Audio 3.0 / 3.1 Plus: 50.4 / 10k chars
Create custom voices by cloning or describing a voice.
Qwen Doc Turbo
Price (Credits)
Input: 20 / 1M tokens
Input: 20 / 1M tokens
Output: 34 / 1M tokens
Extract and analyze information from documents with Qwen.
Qwen Image
Price (Credits)
Qwen Image 2.0: 6.8 / image
Qwen Image 2.0: 6.8 / image
Qwen Image 2.0 Pro: 17 / image
Qwen Image 3.0 Input: 0.68 / image
Qwen Image 3.0 Output: 6.12 / image
Qwen Image 3.0 Pro 1K Output: 8.5 / image
Qwen Image 3.0 Pro 2K Output: 17 / image
Generate images with Qwen Image models.
Qwen Image Edit
Price (Credits)
Qwen Image Edit Plus: 6.8 / image
Qwen Image Edit Plus: 6.8 / image
Qwen Image Edit: 10.2 / image
Qwen Image Edit Max: 17 / image
Edit images with Qwen image models.
Qwen Image Layered
Price (Credits)
12 / image
Separate an image into multiple visual layers.
Qwen Image Translate
Price (Credits)
0.1 / image
Translate text in images while preserving the visual layout.
Qwen OCR
Price (Credits)
Input: 24 / 1M tokens
Input: 24 / 1M tokens
Output: 96 / 1M tokens
Extract text and structured information from images with Qwen3.5-OCR.
Qwen Speech to Text
Price (Credits)
0.0078 / second
Transcribe audio files into text with Qwen ASR.
Qwen Text to Speech
Price (Credits)
Qwen3 Flash: 28.8 / 10k chars
Qwen3 Flash: 28.8 / 10k chars
Qwen-Audio 3.0 Flash: 36 / 10k chars
Qwen-Audio 3.0 / 3.1 Plus: 50.4 / 10k chars
Generate speech audio from text with Qwen voices.
Qwen Text Translation
Price (Credits)
Qwen-MT Flash Input: 30 / 1M tokens
Qwen-MT Flash Input: 30 / 1M tokens
Qwen-MT Flash Output: 90 / 1M tokens
Qwen-MT Plus Input: 90 / 1M tokens
Qwen-MT Plus Output: 270 / 1M tokens
Translate text with Qwen-MT models, terminology, translation memory, and domain guidance.
RedFoxHub
Price (Credits)
4 / request
Search and retrieve public content from Douyin, Xiaohongshu, WeChat, Bilibili, and WeChat Channels.
Remove Background
Price (Credits)
4.2 / image
Cut out subjects and remove image backgrounds.
Seedance Video
Price (Credits)
Fast Image to Video: 594 / 1M tokens
Fast Image to Video: 594 / 1M tokens
Fast Text to Video: 999 / 1M tokens
Image to Video 720p: 756 / 1M tokens
Text to Video 720p: 1,242 / 1M tokens
Image to Video 1080p: 837 / 1M tokens
Text to Video 1080p: 1,377 / 1M tokens
Seedance 2.5 with Video Input 480p or 720p: 1,134 / 1M tokens
Seedance 2.5 without Video Input 480p or 720p: 1,890 / 1M tokens
Seedance 2.5 with Video Input 1080p: 1,242 / 1M tokens
Seedance 2.5 without Video Input 1080p: 2,079 / 1M tokens
Generate videos from prompts and reference media with Seedance 2.0 and 2.5.
SellerSprite MCP
Price (Credits)
1.2 / request
Research Amazon products, keywords, markets, and trademarks with SellerSprite MCP.
Single HTML Website
Price (Credits)
3,000 / 1,000 request
Publish a single HTML website.
Sora 2 Video
Price (Credits)
Text to Video 720p: 72 / second
Text to Video 720p: 72 / second
Text to Video 1080p: 120 / second
Image to Video 720p: 72 / second
Image to Video 1080p: 120 / second
Generate video clips from text prompts or a source image.
Sorftime MCP
Price (Credits)
1 / request
Research products, keywords, markets, and competitors across supported e-commerce platforms.
SunoAPI
Price (Credits)
1.2 / provider credit
Generate music and lyrics with SunoAPI. Music generation uses 12 provider credits per successful call.
Temporary File Service
Price (Credits)
Free
Store temporary files for free. Files may be removed periodically; each file can be up to 500 MB.
TikHub
Price (Credits)
4 / request
Access supported public social data through TikHub.
TinyPNG
Price (Credits)
1.8 / image
Compress PNG, JPEG, and WebP images.
Tongdaxin
Price (Credits)
0.27 / point
Tongdaxin API usage.
UnifAPI
Price (Credits)
0.4 / provider credit
UnifAPI API usage.
Wan 3 Video
Price (Credits)
Wan 3.0 480p: 10.4 / second
Wan 3.0 480p: 10.4 / second
Wan 3.0 720p: 20.8 / second
Wan 3.0 1080p: 41.6 / second
Wan 3.0 Prime 480p: 15.6 / second
Wan 3.0 Prime 720p: 31.2 / second
Wan 3.0 Prime 1080p: 62.4 / second
Generate video clips with Wan 3.0 models.
Wan Image
Price (Credits)
7 / image
Generate and edit images with Wan models.
Wan Video
Price (Credits)
Keyframe Wan 2.2 Flash 480p: 3.4 / second
Keyframe Wan 2.2 Flash 480p: 3.4 / second
Keyframe Wan 2.2 Flash 720p: 6.8 / second
Keyframe Wan 2.2 Flash 1080p: 17 / second
Keyframe Wan 2.1 Plus 720p: 23.8 / second
Image to Video Wan 2.6 Flash 720p Silent: 5.22 / second
Image to Video Wan 2.6 Flash 1080p Silent: 8.7 / second
Image to Video Wan 2.6 Flash 720p Audio: 10.44 / second
Image to Video Wan 2.6 Flash 1080p Audio: 17.4 / second
Image to Video Wan 2.6 720p: 20.88 / second
Image to Video Wan 2.6 1080p: 34.8 / second
Reference to Video Wan 2.6 Flash 720p Silent: 5.22 / second
Reference to Video Wan 2.6 Flash 1080p Silent: 8.7 / second
Reference to Video Wan 2.6 Flash 720p Audio: 10.44 / second
Reference to Video Wan 2.6 Flash 1080p Audio: 17.4 / second
Reference to Video Wan 2.6 720p: 20.88 / second
Reference to Video Wan 2.6 1080p: 34.8 / second
Text to Video Wan 2.6 720p: 20.88 / second
Text to Video Wan 2.6 1080p: 34.8 / second
Generate videos from text, images, keyframes, or reference material with Wan models.
Service
Price (Credits)
Description
AIsa
300 / USD 1 of provider charges
AIsa API usage.
Aura SR
0.24 / second
Upscale images with Aura SR, billed by inference time.
CosyVoice Text to Speech
CosyVoice 3.5 Flash: 28.8 / 10k chars
CosyVoice 3.5 Flash: 28.8 / 10k chars
CosyVoice 3 Flash: 36 / 10k chars
CosyVoice 3.5 Plus: 54 / 10k chars
CosyVoice 3 Plus or 2: 72 / 10k chars
Generate multilingual speech with CosyVoice models.
Doubao Seedream
Flash output: 4.32 / image
Flash output: 4.32 / image
Pro output (≤2.61 MP): 10.8 / image
Pro output (>2.61 MP): 21.6 / image
Pro layer (≤2.61 MP): 5.4 / image
Pro layer (>2.61 MP): 10.8 / image
Pro extra reference (from the second image): 0.72 / image
Generate, edit and split images into layers with Doubao Seedream.
Doubao Speech to Text
68 / hour
Transcribe speech audio into text.
Doubao Text to Speech
154 / 10k chars
Generate speech audio from text with Doubao voices.
GPT Image 2 / 2.5
1K / 2K: 8 / image
1K / 2K: 8 / image
4K: 20 / image
Generate and edit images with GPT Image 2 and 2.5.
iLovePDF
10,400 / 10,000 provider credit
Merge, split, compress, and rotate PDFs, or convert between PDFs and images.
Investoday
1 / point
Investoday API usage.
JEV
20 / 1M tokens
JEV input token usage.
Jina Reader
Read: 10 / 1M tokens
Read: 10 / 1M tokens
Search: 10 / 1M tokens
Read web pages and search web content for agents.
JustOneAPI
60 / CNY 1 of provider charges
JustOneAPI API usage.
Kalodata
40 / provider credit
Kalodata API usage.
Keepa
260 / 1,000 provider token
Keepa API usage.
Kling AI Video
Kling 3.0 or Omni 720p without Native Audio or Video Input: 20.8 / second
Kling 3.0 or Omni 720p without Native Audio or Video Input: 20.8 / second
Kling 3.0 or Omni 1080p without Native Audio or Video Input, or Turbo 720p: ~27.8 / second
Kling 3.0 or Omni 720p with Native Audio or Video Input: 31.2 / second
Kling 3.0 Turbo 1080p: ~34.6 / second
Kling 3.0 or Omni 1080p with Native Audio or Video Input: 41.6 / second
Kling 3.0 or Omni 4K: 104 / second
Generate videos with Kling AI 3.0 models from prompts and reference media.
Kuaidi100 Logistics Tracking
1.4 / request
Track shipments and retrieve real-time logistics updates with Kuaidi100.
LinkFox
0.6 / compute credit
LinkFox API usage.
MiniMax H3
768P input and output video: 14.4 / second
768P input and output video: 14.4 / second
2K input and output video: 23.4 / second
Reference images after the first five: 7.2 / image
Generate videos with MiniMax H3. Input and output video seconds are billed; the first five reference images and input audio are free.
Nano Banana
Nano Banana: 9.4 / image
Nano Banana: 9.4 / image
Nano Banana Edit: 9.4 / image
Nano Banana Pro 1K or 2K: 36 / image
Nano Banana Pro 4K: 72 / image
Nano Banana 2 0.5K: 14.4 / image
Nano Banana 2 1K: 19.2 / image
Nano Banana 2 2K: 28.8 / image
Nano Banana 2 4K: 38.4 / image
Generate and edit images with Nano Banana models.
OOMOL Copy Proofreader
60 / image
Recognize text in images and detect and correct typos in packaging, posters, and other visual copy.
OOMOL RAG
Document indexing: 100 / 1M tokens
Document indexing: 100 / 1M tokens
Query embedding: 100 / 1M tokens
Reranking (enabled by default): 100 / 1M tokens
Document indexing, query embedding and optional reranking are charged separately by actual tokens. Reranking is enabled by default.
Open Flow Run
0.96 / 30 computationSecond
Run Open Flow workflows across apps and services. Waiting time is excluded. Each billable run is rounded up to 30-second blocks, with a 30-second minimum.
Qwen Audio Text to Speech
Qwen-Audio 3.0 Flash: 36 / 10k chars
Qwen-Audio 3.0 Flash: 36 / 10k chars
Qwen-Audio 3.0 / 3.1 Plus: 50.4 / 10k chars
Generate speech with Qwen Audio 3.0 and 3.1 models.
Qwen Custom Voices
Voice Cloning: 0.36 / voice
Voice Cloning: 0.36 / voice
Voice Design: 7 / voice
Qwen-Audio 3.0 Flash: 36 / 10k chars
Qwen-Audio 3.0 / 3.1 Plus: 50.4 / 10k chars
Create custom voices by cloning or describing a voice.
Qwen Doc Turbo
Input: 20 / 1M tokens
Input: 20 / 1M tokens
Output: 34 / 1M tokens
Extract and analyze information from documents with Qwen.
Qwen Image
Qwen Image 2.0: 6.8 / image
Qwen Image 2.0: 6.8 / image
Qwen Image 2.0 Pro: 17 / image
Qwen Image 3.0 Input: 0.68 / image
Qwen Image 3.0 Output: 6.12 / image
Qwen Image 3.0 Pro 1K Output: 8.5 / image
Qwen Image 3.0 Pro 2K Output: 17 / image
Generate images with Qwen Image models.
Qwen Image Edit
Qwen Image Edit Plus: 6.8 / image
Qwen Image Edit Plus: 6.8 / image
Qwen Image Edit: 10.2 / image
Qwen Image Edit Max: 17 / image
Edit images with Qwen image models.
Qwen Image Layered
12 / image
Separate an image into multiple visual layers.
Qwen Image Translate
0.1 / image
Translate text in images while preserving the visual layout.
Qwen OCR
Input: 24 / 1M tokens
Input: 24 / 1M tokens
Output: 96 / 1M tokens
Extract text and structured information from images with Qwen3.5-OCR.
Qwen Speech to Text
0.0078 / second
Transcribe audio files into text with Qwen ASR.
Qwen Text to Speech
Qwen3 Flash: 28.8 / 10k chars
Qwen3 Flash: 28.8 / 10k chars
Qwen-Audio 3.0 Flash: 36 / 10k chars
Qwen-Audio 3.0 / 3.1 Plus: 50.4 / 10k chars
Generate speech audio from text with Qwen voices.
Qwen Text Translation
Qwen-MT Flash Input: 30 / 1M tokens
Qwen-MT Flash Input: 30 / 1M tokens
Qwen-MT Flash Output: 90 / 1M tokens
Qwen-MT Plus Input: 90 / 1M tokens
Qwen-MT Plus Output: 270 / 1M tokens
Translate text with Qwen-MT models, terminology, translation memory, and domain guidance.
RedFoxHub
4 / request
Search and retrieve public content from Douyin, Xiaohongshu, WeChat, Bilibili, and WeChat Channels.
Remove Background
4.2 / image
Cut out subjects and remove image backgrounds.
Seedance Video
Fast Image to Video: 594 / 1M tokens
Fast Image to Video: 594 / 1M tokens
Fast Text to Video: 999 / 1M tokens
Image to Video 720p: 756 / 1M tokens
Text to Video 720p: 1,242 / 1M tokens
Image to Video 1080p: 837 / 1M tokens
Text to Video 1080p: 1,377 / 1M tokens
Seedance 2.5 with Video Input 480p or 720p: 1,134 / 1M tokens
Seedance 2.5 without Video Input 480p or 720p: 1,890 / 1M tokens
Seedance 2.5 with Video Input 1080p: 1,242 / 1M tokens
Seedance 2.5 without Video Input 1080p: 2,079 / 1M tokens
Generate videos from prompts and reference media with Seedance 2.0 and 2.5.
SellerSprite MCP
1.2 / request
Research Amazon products, keywords, markets, and trademarks with SellerSprite MCP.
Single HTML Website
3,000 / 1,000 request
Publish a single HTML website.
Sora 2 Video
Text to Video 720p: 72 / second
Text to Video 720p: 72 / second
Text to Video 1080p: 120 / second
Image to Video 720p: 72 / second
Image to Video 1080p: 120 / second
Generate video clips from text prompts or a source image.
Sorftime MCP
1 / request
Research products, keywords, markets, and competitors across supported e-commerce platforms.
SunoAPI
1.2 / provider credit
Generate music and lyrics with SunoAPI. Music generation uses 12 provider credits per successful call.
Temporary File Service
Free
Store temporary files for free. Files may be removed periodically; each file can be up to 500 MB.
TikHub
4 / request
Access supported public social data through TikHub.
TinyPNG
1.8 / image
Compress PNG, JPEG, and WebP images.
Tongdaxin
0.27 / point
Tongdaxin API usage.
UnifAPI
0.4 / provider credit
UnifAPI API usage.
Wan 3 Video
Wan 3.0 480p: 10.4 / second
Wan 3.0 480p: 10.4 / second
Wan 3.0 720p: 20.8 / second
Wan 3.0 1080p: 41.6 / second
Wan 3.0 Prime 480p: 15.6 / second
Wan 3.0 Prime 720p: 31.2 / second
Wan 3.0 Prime 1080p: 62.4 / second
Generate video clips with Wan 3.0 models.
Wan Image
7 / image
Generate and edit images with Wan models.
Wan Video
Keyframe Wan 2.2 Flash 480p: 3.4 / second
Keyframe Wan 2.2 Flash 480p: 3.4 / second
Keyframe Wan 2.2 Flash 720p: 6.8 / second
Keyframe Wan 2.2 Flash 1080p: 17 / second
Keyframe Wan 2.1 Plus 720p: 23.8 / second
Image to Video Wan 2.6 Flash 720p Silent: 5.22 / second
Image to Video Wan 2.6 Flash 1080p Silent: 8.7 / second
Image to Video Wan 2.6 Flash 720p Audio: 10.44 / second
Image to Video Wan 2.6 Flash 1080p Audio: 17.4 / second
Image to Video Wan 2.6 720p: 20.88 / second
Image to Video Wan 2.6 1080p: 34.8 / second
Reference to Video Wan 2.6 Flash 720p Silent: 5.22 / second
Reference to Video Wan 2.6 Flash 1080p Silent: 8.7 / second
Reference to Video Wan 2.6 Flash 720p Audio: 10.44 / second
Reference to Video Wan 2.6 Flash 1080p Audio: 17.4 / second
Reference to Video Wan 2.6 720p: 20.88 / second
Reference to Video Wan 2.6 1080p: 34.8 / second
Text to Video Wan 2.6 720p: 20.88 / second
Text to Video Wan 2.6 1080p: 34.8 / second
Generate videos from text, images, keyframes, or reference material with Wan models.
App calls are requests made through connected Apps after authorization, including OAuth callbacks, token refreshes, and connection status checks.
