deepseek
DeepSeek: DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Context
1M tokens
Input / 1M tokens
$0.18
Output / 1M tokens
$0.53
Benchmark
—
Pricing
Input tokens$0.18 per 1M tokens
Output tokens$0.53 per 1M tokens
Cache read$0.02 per 1M tokens
Technical details
Model IDdeepseek/deepseek-v4-flash-0731
Context window1M tokens
Input modalitiestext
Output modalitiestext
TokenizerDeepSeek
Max output tokens943,718
Use with MegaBrain
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://getmegabrain.com/api/gateway/v1',
apiKey: process.env.MEGABRAIN_API_KEY,
})
const response = await client.chat.completions.create({
model: 'deepseek/deepseek-v4-flash-0731',
messages: [{ role: 'user', content: 'Hello!' }],
})Ready to use DeepSeek: DeepSeek V4 Flash 0731?
Get an API key and start making requests in minutes.
Get an API key