LLM Token Calculator by /hostbor

Instantly Compare LLM API Prices

Enter Your Text

TOKENIZER

Output Price Input Price Cached Price

Tokens

Words

Chars (no spaces)

Total Characters

Based on OpenAI's base tokenizer (Claude & Gemini compatible)

Pricing Comparison

All Providers

Anthropic

Google

OpenAI

Compare Top LLM Models

FLAGSHIP AI MODELS

PERFORMANCE COMPARISON

o3 High

o4-Mini High

Gemini 2.5 Pro

o1 High

o3 Mini High

Claude 3.7 Sonnet

Grok 3 Mini Beta

DeepSeek R1

o3 High

OpenAI

#1 Overall

Global Average

81.55

Reasoning

93.33

Coding

73.33

Mathematics

84.67

Data Analysis

75.80

Language

76.00

IF Average

86.17

o4-Mini High

OpenAI

#2 Overall

Global Average

78.13

Reasoning

88.11

Coding

74.33

Mathematics

84.90

Data Analysis

70.43

Language

66.05

IF Average

84.96

Gemini 2.5 Pro

Google

#3 Overall

Global Average

77.43

Reasoning

87.53

Coding

58.09

Mathematics

89.16

Data Analysis

79.89

Language

69.31

IF Average

80.59

o1 High

OpenAI

#4 Overall

Global Average

72.18

Reasoning

77.47

Coding

57.14

Mathematics

79.28

Data Analysis

65.47

Language

72.15

IF Average

81.55

o3 Mini High

OpenAI

#5 Overall

Global Average

71.37

Reasoning

74.36

Coding

65.48

Mathematics

76.55

Data Analysis

70.64

Language

56.86

IF Average

84.36

Claude 3.7 Sonnet

Anthropic

#6 Overall

Global Average

70.57

Reasoning

76.17

Coding

44.67

Mathematics

79.00

Data Analysis

74.05

Language

68.27

IF Average

81.25

Grok 3 Mini Beta

xAI

#7 Overall

Global Average

68.33

Reasoning

87.61

Coding

39.71

Mathematics

77.00

Data Analysis

67.87

Language

59.09

IF Average

78.70

DeepSeek R1

DeepSeek

#8 Overall

Global Average

67.47

Reasoning

76.58

Coding

48.48

Mathematics

77.91

Data Analysis

67.60

Language

54.77

IF Average

79.49

AI Model Performance Comparison | Source: Livebench