deepseek-v4-flash API

By DeepSeek

Get an API keyAll models

About

deepseek-v4-flash is available through DeepSeek via a unified, OpenAI-compatible API. Send requests with any OpenAI SDK by pointing the base URL at our gateway — no separate account with the upstream provider required.

Pricing

Input$1 per 1M tokens
Output$2 per 1M tokens
Cache read$0.02 per 1M tokens

Supported endpoints

POST /v1/chat/completionsopenai

Quickstart

curl https://api.getmodel.ai/v1/chat/completions \
  -H "Authorization: Bearer $NEW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"Explain quantum entanglement in one paragraph."}]}'
from openai import OpenAI

client = OpenAI(
    base_url="https://api.getmodel.ai/v1",
    api_key="<YOUR_API_KEY>",
)

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

print(completion.choices[0].message.content)
import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.getmodel.ai/v1',
  apiKey: process.env.NEW_API_KEY,
})

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

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

Replace <YOUR_API_KEY> with a key from your dashboard.

Other DeepSeek models

deepseek-v4-pro$3 / $6 · per 1M tokens

Prices shown are list prices in USD and may vary by user group. Sign in for your exact rate.

XDiscord