DeepSeek·DeepSeek V family

DeepSeek V3

MoEotherReleased Dec 2024

DeepSeek's third-generation large language model featuring mixture-of-experts architecture, strong multilingual capabilities, and competitive performance on reasoning and coding benchmarks.

Capabilities

chatcompletionfunction-callingcode-generationreasoning

Modalities

textcode

Context Window

128K tokens

Providers

available

Available from 2 providers

Cheapest

DeepSeek

$1.37/1M tokens

DeepSeek, Together AI

Providers (2)

Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.

Provider	Pricing (per 1M)	Rate Limits	Regions	Health	Latency
DeepSeek	In: $0.27Out: $1.10	300 RPM / 500K TPM	us-east-1global	Healthy	0ms
Together AI	In: $0.90Out: $0.90	600 RPM / 1.0M TPM	us-east-1us-west-2	Healthy	0ms

Quick Start

Use this model via DeepSeek with an OpenAI-compatible SDK.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.deepseek.com/v1",
  apiKey: process.env.DEEPSEEK_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek-chat",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

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

Using DeepSeek API • OpenAI-compatible SDK