deepseek-ai/deepseek-v4-flash — Free API

What is deepseek-ai/deepseek-v4-flash?

DeepSeek V4 Flash is available free on NVIDIA NIM with up to 40 RPM and no daily token cap. As DeepSeek's latest-generation flash variant, it prioritizes speed and efficiency while retaining strong general-purpose performance. NVIDIA's OpenAI-compatible endpoint makes it a drop-in replacement for any tool that accepts a custom base URL. NVIDIA Developer Program membership (free) required; phone verification needed for API key.

deepseek-ai/deepseek-v4-flash API Code Example

Paste your API key and run. See the config generator for Claude Code, Cursor, and more tools.

from openai import OpenAI

client = OpenAI(
    base_url="https://integrate.api.nvidia.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="deepseek-ai/deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

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

const completion = await openai.chat.completions.create({
  model: "deepseek-ai/deepseek-v4-flash",
  messages: [{ role: "user", content: "Hello!" }],
});

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

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "deepseek-ai/deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from NVIDIA NIM