MiniMax M2.5 is LiveMiniMax M2.5 is Live on Canopy Wave. Try it Now!DeepSeek V3.1
DeepSeek V3.1 API
LLMReasoning

DeepSeek V3.1 API

All You Need To Know About DeepSeek V3.1 API

Overview

Model Provider:DeepSeek
Model Type:LLM/Reasoning
State:Take offline

Key Specs

Quantization:FP8
Parameters:671B (37B activated)
Context:128k
Take offline
Quick Start
Reserve Dedicated Endpoint

Introduction

DeepSeek-V3.1 is a large hybrid reasoning model that uniquely supports both a "thinking" and a "non-thinking" mode, which can be controlled via prompt templates.

Built upon the DeepSeek-V3 architecture with 37 billion active parameters (out of 671B total), it has been post-trained for an extended 128K long-context window. This version introduces significant improvements in tool calling, agentic tasks, and reasoning efficiency, achieving performance comparable to earlier high-end models but with faster response times. These enhancements make it ideal for complex coding, research, and agentic workflows.

DeepSeek V3.1 API Usage

Model

Endpoint

deepseek/deepseek-chat-v3.1


        1
        curl -X POST https://inference.canopywave.io/v1 \
      
        2
          -H "Content-Type: application/json" \
      
        3
          -H "Authorization: Bearer $CANOPYWAVE_API_KEY" \
      
        4
          -d '{
      
        5
            "model": "deepseek/deepseek-chat-v3.1",
      
        6
            "messages": [
      
        7
              {"role": "system", "content": "You are a helpful assistant."},
      
        8
              {"role": "user", "content": "please tell me a story."}
      
        9
            ],
      
        10
          }'
PromotionContact us