← All models
DeepSeek V4 Flash — text model on LumeAPI

DeepSeek V4 Flash

deepseek/deepseek-v4-flash

Cheaper. More stable. One-stop API aggregation.

Introduction

DeepSeek V4 Flash is the faster/cheaper DeepSeek whitelist option.

Model id `deepseek/deepseek-v4-flash` works on chat completions.

Prefer it for high-volume DeepSeek traffic where Flash-class quality is enough.

Pricing

Official$0.10 / $0.20 per 1M (in/out)
LumeAPI$0.10 / $0.20 per 1M (in/out)
per 1M tokens (in/out)
Last updated: July 2026Source: provider list price

Endpoint

Base URL: https://api.lumeapi.site/v1

Auth: Authorization: Bearer <your-lumeapi-key>

Developer docs

Open the integration notes for this model, or the modality guide for request fields and polling.

Call exampledeepseek/deepseek-v4-flash
curl https://api.lumeapi.site/v1/chat/completions \
  -H "Authorization: Bearer $LUMEAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "messages": [{"role":"user","content":"Hello"}]
  }'