ModelsDeepSeek V3.1
DeepSeek V3.1
deepseek-ai/DeepSeek-V3.1DeepSeek V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes.
ThinkingToolsRAG
CreativeRoleplay
Context
16K
Speed
Fast
Capabilities
Chat Completions
VisionNo
ThinkingYes
ToolsYes
InternetNo
RAGYes
InputText
OutputText
Parameters
| Parameter | Values | Recommended | |
|---|---|---|---|
| Temperature | min0 | max1 | 0.8 |
| Top P | min0 | max1 | 0.9 |
| Top K | min1 | max100 | 40 |
| Freq. Penalty | min-2 | max2 | 0 |
| Pres. Penalty | min-2 | max2 | 0 |
| Rep. Penalty | min1 | max2 | 1 |
| Max Tokens | min1 | max1024 | 512 |
Credit Cost per Plan
FreeN/A
Basic4 cr/req
≈ 250 req/month
Starter3 cr/req
≈ 666 req/month
Pro3 cr/req
≈ 1,000 req/month
Pro+2 cr/req
≈ 2,500 req/month
Max2 cr/req
≈ 6,000 req/month
Max+2 cr/req
≈ 12,500 req/month
Ultimate2 cr/req
≈ 25,000 req/month
Context Window
16K
16,384 tokens