DeepSeek

Serious reasoning at bargain prices, with welcome credits.

DeepSeek serves V4 Flash, V4 Pro and an experimental Flash Vision model from the source. OpenAI-compatible (and Anthropic-compatible), with a granted balance on sign-up rather than a standing daily quota. After that it is pay-as-you-go. Limits flex with load.

1M of context, thinking or not on the same id — the old chat/reasoner split is gone. No card to start. If you want DeepSeek without going through a router, this is the door. Docs live at api-docs.deepseek.com.

Free models: 3
Max context: 1M
Free tier: Credits on sign-up
Requirement: Email account, no card

Endpoint

Base URLhttps://api.deepseek.com/v1

Env varDEEPSEEK_API_KEY

Rate limitDynamic, based on load

OpenAI-compatible
text
image

Code examples

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.deepseek.com/v1',
  apiKey: process.env.DEEPSEEK_API_KEY
})

const response = await client.chat.completions.create({
  model: 'deepseek-v4-flash',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.deepseek.com/v1",
    api_key=os.environ["DEEPSEEK_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

curl https://api.deepseek.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DEEPSEEK_API_KEY" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

Models you get for free3

DeepSeek V4 Flashdeepseek-v4-flash
DeepSeek V4 Prodeepseek-v4-pro
DeepSeek V4 Flash Visiondeepseek-v4-flash-vision-exp