DeepSeek
DeepSeek V4 Pro
DeepSeek V4 Pro offers four thinking levels — None, Low, High, and Max — so you can trade response speed for thinking depth.
Quick facts
Pricing
Input $0.66-$1.32 / Output $1.98-$3.96 per 1M tokens, off-peak to peak
Context window
1M
Max output
384K
Knowledge cutoff
2025-05
Reasoning levels
DeepSeek V4 Pro comes with 4 selectable reasoning levels. Pick the level right in the crowSync composer — higher levels think longer on hard problems (and use more output tokens); token prices stay the same at every level.
None
DeepSeek V4 Pro No Thinking
Low
DeepSeek V4 Pro Low
High
DeepSeek V4 Pro High
Max
DeepSeek V4 Pro Max
What this model can do
You provide
- 💬 Text instructions
It creates
- 📝 Formatted text & summaries
- 💻 Code snippets
- 🤖 JSON & structured data
- 🎨 Generated images
Capabilities
Reasoning
Better suited to multi-step analysis, planning, and harder prompts.
Vision
Text-only in crowSync today.
Document input
Does not expose native document input in crowSync.
Structured output
Can return JSON for workflows that need machine-readable output.
Tool use
Can use compatible tools when crowSync enables them for the run.
Native tools in crowSync
Web search
Search the live web during a run.
Available
Image generation
Generate images directly from prompts.
Available
Input and output
Input
- Text
Output
- Text
Common use cases
- Complex planning, debugging, and multi-step analysis.
- Research tasks that need current information from the web.
Pricing details
Input (off-peak)
$0.66 / 1M tokens
Output (off-peak)
$1.98 / 1M tokens
Cached input (off-peak)
$0.022 / 1M tokens
Input (peak)
$1.32 / 1M tokens
Output (peak)
$3.96 / 1M tokens
Cached input (peak)
$0.044 / 1M tokens
Peak hours
01:00-04:00 and 06:00-10:00 UTC, Monday to Friday, except Chinese public holidays