DeepSeek·DeepSeek R1 family

DeepSeek R1

Open WeightsmitReleased Jan 2025

DeepSeek's reasoning-focused model trained with reinforcement learning for complex multi-step reasoning. Excels at math, science, and coding problems requiring chain-of-thought reasoning.

Capabilities

chatcompletioncode-generationreasoning

Modalities

textcode

Context Window

131K tokens

Providers

available

Available from 5 providers

Cheapest

Groq

$1.74/1M tokens

Fastest

Groq

80ms TTFT

Deep Infra, DeepSeek, Groq, SiliconFlow, Together AI

Providers (5)

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
Groq	In: $0.75Out: $0.99	30 RPM / 100K TPM	us-east-1	Healthy	80ms
Deep Infra	In: $0.40Out: $1.60	600 RPM / 1.0M TPM	us-east-1eu-west-1	Healthy	0ms
DeepSeek	In: $0.55Out: $2.19	500 RPM / 1.0M TPM	us-east-1global	Healthy	0ms
SiliconFlow	In: $0.55Out: $2.19	300 RPM / 500K TPM	ap-east-1global	Healthy	0ms
Together AI	In: $3.00Out: $7.00	600 RPM / 1.0M TPM	us-east-1us-west-2	Healthy	0ms

Quick Start

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

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "deepseek-r1-distill-llama-70b",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

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

Using Groq API • OpenAI-compatible SDK