New version available

Refresh to update

Could not apply changes

DeepSeek V4 Flash 0731

openrouter
deepseek/deepseek-v4-flash-0731

Fast DeepSeek V4 model for agentic workflows, coding, and multi-step reasoning. Supports function calling and is hosted on Cloudflare Workers AI.

Quick start

TypeScript
cURL
import OpenAI from 'openai'

const openai = new OpenAI({
  apiKey: process.env.CODEPLATFORM_API_KEY,
  baseURL: 'https://ai.codeplatform.net/v1',
})

const response = await openai.chat.completions.create({
  model: 'deepseek/deepseek-v4-flash-0731',
  messages: [{
    role: 'user',
    content: 'Hello world',
  }],
})

API details

Send requests to the OpenAI-compatible /v1/chat/completions endpoint.

Capabilities

Pricing

Input tokens (per 1M)$0.44
Output tokens (per 1M)$1.32
Cached input (per 1M)$0.014

Limits

Context length1,310,720 tokens
Max output943,718 tokens