First month for free!

Get started

Lemonfox.ai

Lemonfox.ai

Docs
Easy-to-use AI API

DeepSeek API

Run DeepSeek V4 Flash through an OpenAI-compatible chat API — same SDK, lower cost, and a 1M-token context window.

Similar Score, Lower Cost

$0.50 / 1M

Lemonfox DeepSeek V4 Flash

Intelligence Index 52

$1.20 / 1M

OpenAI GPT-5.6 Luna output

Intelligence Index 52 (max)

DeepSeek V4 Flash scores similarly to GPT-5.6 Luna (max) on the Artificial Analysis leaderboard and is more than half as expensive.

Get StartedRead Docs

OpenAI-Compatible

Point the OpenAI SDK at https://api.lemonfox.ai/v1, set model to deepseek-v4-flash, and keep your existing chat completions code.

Strong Quality / Price

DeepSeek V4 Flash matches GPT-5.6 Luna (max) at Intelligence Index 52 on Artificial Analysis, and is more than half as expensive — with a 1M-token context window.

$0.50 per 1M Tokens

Flat pricing at $0.50 per 1 million tokens. Need stronger reasoning or coding? Use mimo-v2.5-pro at $1.25/1M on the same API key.

Simple API Setup

Create a chat completion with model: "deepseek-v4-flash". Streaming works via stream: true.

// npm install --save openai or yarn add openai
import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.lemonfox.ai/v1",
});

const completion = await openai.chat.completions.create({
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "How many days are in a year?" },
  ],
  model: "deepseek-v4-flash",
});

console.log(completion.choices[0].message.content);
Read Docs

Frequently Asked Questions

Get Started

Other APIs: Chat API Docs, Whisper API, Subtitle API, Speaker Diarization API