Limited-time offer: Limited-time offer: Get 50% off DeepSeek-V4.1-Flash-1017. Try it nowArrow
Hy4-flash API
VISION
Hy4-flash API

All You Need to Know About Hy4-flash API

Overview

Model Provider:Tencent
Model Type:Vision
State:Ready

Key Specs

Quantization:FP8
Parameters:224B
Context:1M
Pricing:$0.07 input / $0.29 output / $0.003 cache
Try Model API
Quick Start
Reserve Dedicated Endpoint

Introduction

Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens.

Its 42-layer language backbone consists of one dense feed-forward layer and 41 MoE layers, with identity Hyper-Connections (iHC) supporting inter-layer information flow. A vision encoder (adapted from SigLIP2-So400m-Patch16-Res512) is connected to the backbone through an MLP projector. In addition to the backbone, a built-in 5-layer drafter, DFly2 (0.85B parameters), reuses the target model's KV cache and sparse indices to support long-context speculative decoding at a low, constant cost.

Hy4-flash API Usage

Model

Endpoint

tencent/hy4-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": "tencent/hy4-flash",
      
        6
            "messages": [
      
        7
              {"role": "user", "content": "tell me a story"}
      
        8
            ],
      
        9
            "max_tokens": 1000,
      
        10
            "temperature": 0.7
      
        11
          }'