Side-by-Side Comparison

Claude 3.5 Sonnet vs Llama 3.1 405b

Compare API pricing, context window, benchmarks, and performance. Claude 3.5 Sonnet is the same price as Llama 3.1 405b.

Claude 3.5 SonnetAnthropic

Llama 3.1 405bFireworks

Metric

Claude 3.5 Sonnet

Llama 3.1 405b

Provider

Anthropic

Fireworks

License

Proprietary

Open Source

Release Date

2024-06-20

2024-07-23

Pricing (per 1M tokens)

Input Price0%

$3.00

Output Price+400%

$15.00

$3.00

Blended (1M + 1M)

$18.00

$6.00

Model Details

Context Window

200K

128K

Max Output Tokens

8.2K

Knowledge Cutoff

April 2024

December 2023

Throughput

78 tok/s

N/A

Benchmarks

GPQA Diamond

65%

—

SWE Bench

49%

—

AIME 2024

16%

—

MATH 500

78%

—

BFCL

56.5%

—

Alder Polyglot

51.6%

—

MMLU

90.4%

85.2%

MMMU

68.3%

54%

HellaSwag

95.4%

88.3%

HumanEval

96.4%

86.8%

MATH

71.1%

73.8%

Verdict

The Bottom Line

Llama 3.1 405b offers significantly lower pricing, while Claude 3.5 Sonnet leads on benchmark performance. Your choice depends on whether cost efficiency or raw capability matters more for your use case.

← View Claude 3.5 Sonnet Details Browse All Models →

From the Editor

Building an AI app?

Skip weeks of setup. AnotherWrapper gives you 10+ production-ready AI templates with auth, payments, and APIs pre-configured.

View Apps Get it — $249

All Large Language Models

Anthropic

20 models

Claude Sonnet 4.6·Claude Opus 4.6·Claude Opus 4.5·Claude Haiku 4.5·Claude Sonnet 4.5·Claude Opus 4·Claude Sonnet 3.7·Claude Haiku 3.5·Claude 3 Haiku·Claude Haiku 3·Claude 3 Opus·Claude 3 Sonnet·Claude Opus 3·Claude 2.1·Claude Instant 1.2·Claude 2·Claude 3.5 Haiku·Claude Sonnet 3.5·Claude Sonnet 4

Google

13 models

Gemini 3 Pro Preview·Gemini 2.5 Pro·Gemini 2.0 Flash·Gemini 1.5 Pro·Gemini 1.5 Flash·Gemini 1.5 Flash·Gemini 1.5 Pro·Gemini 1.5 Flash 8B·Gemini 2.0 Flash Lite·Gemini 2.5 Flash·Gemini 2.5 Flash Lite·Gemini 3 Flash Preview·Gemini 3.1 Flash Lite Preview

Perplexity

5 models

Llama 3.1 70b·Sonar·R1 1776·Sonar Deep Research·Sonar Pro

xAI

10 models

Grok Code Fast 1·Grok 3·Grok 2·Grok 2 Vision·Grok 3 Fast·Grok 3 Mini·Grok 3 Mini Fast·Grok 4·Grok 4 Fast·Grok 4.1 Fast

DeepSeek

7 models

DeepSeek V2·DeepSeek R1·DeepSeek V3·DeepSeek V3.1·DeepSeek V3.2·deepseek-chat·deepseek-coder

Groq

9 models

Llama 4 Maverick (Groq)·Llama 4 Scout (Groq)·DeepSeek R1 (Groq)·Llama 3.3 70B (Groq)·Llama 3.1 70b·Llama 3.1 8B (Groq)·Mixtral 8x7B·Mistral Small 2503 (Groq)·Qwen QwQ 32B (Groq)

MiniMax

3 models

MiniMax M2·MiniMax M2.1·MiniMax M2.5

Qwen

12 models

Qwen Plus Latest·Qwen 3 14B·Qwen 3 30B A3B·Qwen 3 8B·Qwen 2.5 72B Instruct·Qwen 3 235B A22B·Qwen 3 32B·Qwen 3 4B·Qwen 3.5 397B A17B·Qwen Max Latest·Qwen QwQ Plus·Qwen Turbo Latest

01.ai

1 models

Yi-Large

AI21 Labs

2 models

Jamba 1.5 Large·Jamba 1.5 Mini

Amazon

7 models

Amazon Nova 2 Lite·Amazon Nova Lite·Amazon Nova 2 Omni·Amazon Nova Premier·Amazon Nova Micro·Amazon Nova Pro·Amazon Nova 2 Pro

Anyscale

2 models

Llama 3 70b·Mixtral 8x7B

Cerebras

5 models

Llama 3.3 70B (Cerebras)·DeepSeek R1 (Cerebras)·DeepSeek V3 (Cerebras)·Llama 3.1 8B (Cerebras)·Qwen 2.5 32B (Cerebras)

Cohere

4 models

Command R7B·Command R·Command R+·Command A

DeepInfra

6 models

Llama 3.3 70B (DeepInfra)·Llama 3.1 405B (DeepInfra)·DeepSeek R1 (DeepInfra)·DeepSeek V3 (DeepInfra)·Mistral Small 2501 (DeepInfra)·Qwen 2.5 72B (DeepInfra)

Fireworks

10 models

DeepSeek V3.2 (Fireworks)·DeepSeek R1 (Fireworks)·Llama 4 Maverick (Fireworks)·Llama 3.1 405B (Fireworks)·Llama 3.1 70b·Yi-Large·Mixtral 8x7B·Kimi K2.5 (Fireworks)·Llama 4 Scout (Fireworks)

Hyperbolic

4 models

Llama 3.1 405B (Hyperbolic)·DeepSeek R1 (Hyperbolic)·DeepSeek V3 (Hyperbolic)·Qwen 3 235B A22B (Hyperbolic)

IBM Watsonx

6 models

Granite 3.1 8B Instruct·Llama 3.1 405b·Llama 3.1 70b·Mistral Large·Granite 3.1 2B Instruct·Granite 3.2 8B Instruct

Mistral

18 models

Codestral·Mistral Small 3.1·Mistral Large 2411·Pixtral Large 2411·Mistral Large 2·Mistral Large·Mistral 7B Instruct·Magistral Medium·Magistral Small·Mistral Codestral·Mistral Devstral·Mistral Devstral 2·Mistral Devstral Small 2·Mistral Medium 3·Mistral Ministral 3B·Mistral Ministral 8B·Mistral Nemo·Mistral Nemo 2407

Moonshot AI

2 models

Kimi K2 Thinking·Kimi K2.5

Nebius AI Studio

5 models

Qwen 3 235B A22B (Nebius)·DeepSeek V3 (Nebius)·DeepSeek R1 (Nebius)·Llama 3.1 405B (Nebius)·Llama 3.1 70B (Nebius)

Reka

3 models

Reka Core·Reka Edge·Reka Flash

Replicate

5 models

DeepSeek R1 (Replicate)·Llama 3.1 405b·Llama 3.1 405B (Replicate)·Llama 3.1 70b·Mixtral 8x7B

SambaNova Cloud

5 models

Llama 3.3 70B (SambaNova)·Qwen 2.5 72B (SambaNova)·Llama 3.1 405B (SambaNova)·DeepSeek R1 (SambaNova)·DeepSeek V3 (SambaNova)

Together.AI

10 models

Llama 4 Maverick (Together)·Llama 4 Scout (Together)·DeepSeek R1 (Together)·Llama 3.3 70B (Together)·Llama 3.1 405b·Llama 3.1 405B (Together)·Llama 3.1 70b·Mixtral 8x7B·DeepSeek V3 (Together)·Qwen 2.5 72B (Together)

Writer

8 models

Palmyra X 004·Palmyra Fin 32k·Palmyra Med 32k·Palmyra X 002·Palmyra X 002 32k·Palmyra X 003·Palmyra X 32k·Palmyra X5

Z AI

6 models

GLM-5 Code·GLM-4.6·GLM-4.5·GLM-4.5 Flash·GLM-4.7·GLM-5

From the founder

Built from production, not theory.

Everything here comes from real products with real users paying real money. 200K+ of them.

Fekri

Founder & Engineer

@fekdaoui

I've been building AI apps since GPT-3 and shipped more than 15 of them to over 200K users. I realized I was doing the same thing over and over: set up auth, handle Stripe webhooks, build embedding pipelines, add rate limiting, configure model routing...

About 70% of every new project was copy-pasting from the last one. So I turned it into a proper codebase and built AnotherWrapper for 3 reasons:

Skip the first 2-3 months of setup and go straight to building your product
Avoid the headaches I already solved (payments, emails, auth, vector stores)
Get profitable fast, the more you ship the more you learn

I use this for every new product I launch. Same codebase, same foundation.

It also includes 8 production-ready demo apps so you can pick what you need and start building from there.

15+

AI apps shipped to production

3 yrs

building with AI APIs

200K+

users across products

200+

hours saved per project

What you get

8 production-ready AI app templates
Auth, payments, emails, fully integrated
Vector embeddings, RAG, model switching
Rate limiting, error handling, analytics
Lifetime access + all future updates

Get AnotherWrapper

One-time purchase, lifetime access

$249

$349

View Demo Apps

FAQ

Frequently asked questions

Questions about access, updates, licensing, or how the codebase works? Start here.

Still have questions? Email us at [email protected]

Claude 3.5 Sonnet vs Llama 3.1 405b