Upgrade Your API Integration to DeepSeek-V4 Immediately
Point your API calls to v4-pro or v4-flash today.
Manually update your model parameters to 'deepseek-v4-pro' or 'deepseek-v4-flash' to access the latest V4 generation via standard OpenAI or Anthropic interfaces.
The Scenario
You are a developer or power user with an existing automation script or app that uses an LLM, and you want to upgrade to the latest, most powerful version of DeepSeek (V4-Pro) to improve performance.
Before & after
Developers would wait for months for model updates or manually rewrite integration code for entirely new APIs. Switching backends could take 30-60 minutes or more depending on documentation clarity.
By changing your base URL and model ID to v4-pro or v4-flash, you can immediately access the latest capabilities. This configuration change takes about 2-3 minutes.
The Prompt
// When creating your client, update your configuration:
const client = new OpenAI({
baseURL: 'https://api.deepseek.com',
apiKey: '[YOUR_API_KEY]'
});
const response = await client.chat.completions.create({
model: 'deepseek-v4-pro',
messages: [{ role: 'user', content: '[YOUR_COMPLEX_QUERY]' }]
});The DeepSeek API now supports both OpenAI and Anthropic interfaces for V4 models, allowing for easier integration into existing workflows that use those standards.
Source
Change Log | DeepSeek API Docs"To access the new models, the base_url remains unchanged, and the model parameter should be set to `deepseek-v4-pro` or `deepseek-v4-flash`."