Models/deepseek

deepseek-v4-flash· Released Apr 24, 2026

Name: deepseek-v4-flash
Brand: deepseek

deepseek/deepseek-v4-flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Input

From$0.126/M

Output

From$0.252/M

Context

Up to 1M

Max output

Up to 393K

Modalities

TextText

Input and output show the lowest price across upstreams, for reference. Your actual prices are listed per upstream below.

Upstreams & pricing

Upstream	Context	Max output	Input $/1M	Output $/1M	Cached input $/1M
Zenlayer AI Gateway-openai_compat (Global)From price	1M	393K	$0.126	$0.252	$0.002

Routed in real time — you pay the listed price of whichever upstream serves your call.

How to call

curlrequest.sh

curl https://api.tkex.ai/v1/chat/completions \
  -H "Authorization: Bearer $TX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "messages": [
      {"role": "user", "content": "Say hello in five words."}
    ]
  }'