Back to Models

Llama 3.3 70B

![Meta](https://artificialanalysis.ai/img/logos/meta_small.svg)Meta
14/ 57

Intelligence Score

Intelligence

14

#162 of 212 (top 76%)

Speed

90 tok/s

#79 of 141

Price

$0.62

per M tokens

#64 cheapest of 142

Context Window

128K

tokens

Latency: 1ms (#57)

Score Breakdown

Quality Score23%
Speed Score12%
Cost Score94%

Similar Models

Llama 3.1 Nemotron Nano 4B v1.1

![NVIDIA](https://artificialanalysis.ai/img/logos/nvidia_small.svg)NVIDIA

14intelligence

Kimi Linear 48B A3B Instruct

![Kimi](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Fkimi_small.png&w=32&q=75)Kimi

14intelligence

Llama 3.3 Nemotron Super 49B

![NVIDIA](https://artificialanalysis.ai/img/logos/nvidia_small.svg)NVIDIA

14intelligence

Ring-flash-2.0

![InclusionAI](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Finclusionai_small.jpg&w=32&q=75)InclusionAI

14intelligence

Solar Pro 2

![Upstage](https://artificialanalysis.ai/img/logos/upstage_small.svg)Upstage

14intelligence

Use This Model

Claude Code

claude --model llama-3-3-instruct-70b

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "llama-3-3-instruct-70b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("llama-3-3-instruct-70b"),
  prompt: "Hello",
});
Back to Models