Pro/deepseek-ai/DeepSeek-V3.1-Terminus

Pro/deepseek-ai/DeepSeek-V3.1-Terminus

Silicon-based DeepSeek-V3.1-Terminus for Mobile Deployment
2025-09-22
LLM
Model capability: function_call
Input:
$0.5715/1M tokens
Output:
$1.715/1M tokens
Bulk order? Contact your manager for exclusive deals

API Overview

DeepSeek-V3.1-Terminus is an updated version of the V3.1 model released by DeepSeek, positioned as a hybrid agent-based large language model. This update focuses on addressing user feedback issues and enhancing stability while preserving the model's original capabilities. It significantly improves language consistency, reducing instances of mixed Chinese-English usage and abnormal characters. The model integrates "Thinking Mode" and "Non-thinking Mode," allowing users to seamlessly switch between them via chat templates to suit various tasks. As a key optimization, V3.1-Terminus boosts the performance of the Code Agent and Search Agent, making them more reliable in tool calls and executing complex multi-step tasks.

Playground

Log in to explore more features! Click to Log In

API Analytics

API Reference (1)

API DescriptionAPI EndpointRequest MethodStabilityParameter Description
Chat(SiliconFlow)
POST
Stable
View Details

API Pricing

$
ModelDescriptionContextOfficial Price302.AI Price

Pro/deepseek-ai/DeepSeek-V3.1-Terminus

-
160000

Input$0.5715 / 1M tokens
Output$1.715 / 1M tokens

Input$0.5715/ 1M tokens
Output$1.715/ 1M tokens
Original Price