Back to all models

DeepSeek V3.1

Updated DeepSeek V3 with tools and improved performance.

deepseek-v3.1
STABLEGet StartedView uptime
128,000 context
Starting at $0.56/M input tokens
Starting at $1.68/M output tokens
Streaming
Tools
Reasoning

Select Provider

All Providers for DeepSeek V3.1

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

ByteDance
Context: 128k
Input
$0.56
/M tokens
Cached
$0.112
/M tokens
Output
$1.68
/M tokens
Get Started