Model API

DeepSeek V4 Flash 0731 API

DeepSeek's July 31 V4 Flash release for long-context reasoning, structured output, and agent tool use.

Model ID

deepseek-v4-flash

Provider

zenmux

Capability

chat

Status

Available

Pricing and limits

tokens in

$0.44 / 1M input tokens

tokens out

$1.32 / 1M output tokens

Context length: 1,000,000
Max output: 393,216
Release date: 2026-07-31

Use this model

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AIDUCT_API_KEY,
  baseURL: "https://api.aiduct.ai/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Say hello in one sentence." }],
});

Supported parameters

messagestemperaturetop_pmax_tokensstreamstoptoolstool_choiceresponse_formatuserthinking

Related API pages

API referenceEndpoint docs, authentication, and examples.Pricing tableCompare every public model and billing unit.PlaygroundTest requests from the browser before integrating.

This model page is backed by the live Aiduct model catalog. Long-form generated notes are not available for this slug yet, but the model ID, provider, pricing rows, and supported parameters above are still crawlable.