/Models/DeepSeek: DeepSeek V3.1
DeepSeek

DeepSeek: DeepSeek V3.1

33k context
Lowest Price
$0.15
per 1M tokens
Providers
1
Available
Context
33k
tokens

Price Comparison

ProviderInput / OutputLatencyStatus
OpenRouterOpenRouterLowest
$0.15/$0.75
...
Verified

About This Model

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient i...

Quick Start