📊Ai

AIモデル比較ツール

さまざまなAIモデルを機能、トークン制限、コストに基づいて評価・比較します。どのモデルが最適かを決定する開発者にとって必須のツールです。

Models to show

Model	Provider	Context	Max output	Input / 1M	Output / 1M
GPT-4o	OpenAI	128,000	16,384	$2.5	$10
GPT-4o mini	OpenAI	128,000	16,384	$0.15	$0.6
GPT-4 Turbo	OpenAI	128,000	4,096	$10	$30
Claude 3.5 Sonnet	Anthropic	200,000	8,192	$3	$15
Claude 3 Haiku	Anthropic	200,000	4,096	$0.25	$1.25
Claude 3 Opus	Anthropic	200,000	4,096	$15	$75
Gemini 1.5 Pro	Google	2,000,000	8,192	$1.25	$5
Gemini 1.5 Flash	Google	1,000,000	8,192	$0.075	$0.3
Llama 3.1 70B	Meta	131,072	4,096	$0.9	$0.9
Llama 3.1 8B	Meta	131,072	4,096	$0.18	$0.18

GPT-4o (OpenAI)
  Context: 128,000
  Output: 16,384
  Input: $2.5/M
  Output: $10/M

GPT-4o mini (OpenAI)
  Context: 128,000
  Output: 16,384
  Input: $0.15/M
  Output: $0.6/M

GPT-4 Turbo (OpenAI)
  Context: 128,000
  Output: 4,096
  Input: $10/M
  Output: $30/M

Claude 3.5 Sonnet (Anthropic)
  Context: 200,000
  Output: 8,192
  Input: $3/M
  Output: $15/M

Claude 3 Haiku (Anthropic)
  Context: 200,000
  Output: 4,096
  Input: $0.25/M
  Output: $1.25/M

Claude 3 Opus (Anthropic)
  Context: 200,000
  Output: 4,096
  Input: $15/M
  Output: $75/M

Gemini 1.5 Pro (Google)
  Context: 2,000,000
  Output: 8,192
  Input: $1.25/M
  Output: $5/M

Gemini 1.5 Flash (Google)
  Context: 1,000,000
  Output: 8,192
  Input: $0.075/M
  Output: $0.3/M

Llama 3.1 70B (Meta)
  Context: 131,072
  Output: 4,096
  Input: $0.9/M
  Output: $0.9/M

Llama 3.1 8B (Meta)
  Context: 131,072
  Output: 4,096
  Input: $0.18/M
  Output: $0.18/M

Was this result accurate?

How it works

This aiモデル比較ツール runs entirely in your browser — no data is sent to any server. Simply fill in the fields above and the result updates instantly. You can copy the output with the copy button provided.