deepseek
DeepSeek: DeepSeek V3.1
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...
Input Cost
$0.21
per 1M tokens
Output Cost
$0.79
per 1M tokens
Context Window
163,840
tokens
Developer ID: deepseek/deepseek-chat-v3.1
Related Models
deepseek
$0.27/1M
DeepSeek: DeepSeek V3.1 Terminus
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that ...
deepseek
$0.70/1M
DeepSeek: R1 Distill Llama 70B
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-...
deepseek
$0.23/1M
DeepSeek: DeepSeek V3.2
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficienc...