Canopy Wave & SAIHEACanopy Wave & SAIHEAT Announce Merger Agreement | Learn MoreArrow
DeepSeek-V4.1-Flash API
VISION

DeepSeek-V4.1-Flash API

All You Need to Know About DeepSeek-V4.1-Flash API

Overview

Model Provider:DeepSeek
Model Type:VISION/LLM
State:Ready

Key Specs

Quantization:FP8
Parameters:552B
Context:1M
Pricing:$0.30 input / $1.20 output / $0.006 cache
Try Model API
Quick Start
Reserve Dedicated Endpoint

Introduction

We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.

DeepSeek-V4.1-Flash API Usage

Model

Endpoint

deepseek/deepseek-v4.1-flash


        1
        curl -X POST https://inference.canopywave.io/v1/chat/completions \
      
        2
          -H "Content-Type: application/json" \
      
        3
          -H "Authorization: Bearer $CANOPYWAVE_API_KEY" \
      
        4
          -d '{
      
        5
            "model": "deepseek/deepseek-v4.1-flash",
      
        6
            "messages": [
      
        7
              {"role": "user", "content": "tell me a story"}
      
        8
            ],
      
        9
            "max_tokens": 1000,
      
        10
            "temperature": 0.7
      
        11
          }'