25+ AI Models Available

AI Model Explorer

Find the perfect AI model for your needs. Compare performance, pricing, and capabilities across providers.

Last updated: January 2026

AI Model Intelligence Engine

Paste your prompt to find the perfect model

Recent Updates

Live
Jan 3
New

Added MMLU, HumanEval, and MT-Bench scores to all models

Jan 2
-50%

GPT-4o pricing reduced from $5/$15 to $2.50/$10 per 1M tokens

openai
Dec 15
New

Gemini 2.0 Flash released with improved speed and multimodal support

google
Dec 10
New

Claude 3.5 Haiku launched - fastest and most affordable Claude model

anthropic
Nov 20
-25%

Claude 3.5 Sonnet output price reduced

anthropic
Nov 1
New

Grok 2 released with 128K context and improved reasoning

xai
Calculate cost for:tokens
12
Models Available
$0.08/1M
Cheapest Model
~0.8s
Fastest Response
200k tokens
Max Context
OpenAI

OpenAI

4 models • 1 recommended

GPT-4o Mini

Modelgpt-4o-mini
Context128K
SpeedVery Fast
Perf86%
Cost Effective
Chat
Quick Tasks
Benchmark Scores
MMLU82
Code87
Chat87.5
$0.38/1M tokensAverage
Input$0.1
Output$0.6
Your cost$0.38

GPT-4o

Rec
Modelgpt-4o
Context128K
SpeedFast
Perf90%
General Purpose
Coding
Analysis
Benchmark Scores
MMLU88.7
Code90.2
Chat91.3
$6.25/1M tokensAverage
Input$2.5
Output$10.0
Your cost$6.25

o1-mini

Modelo1-mini
Context128K
SpeedUltra Fast
Perf89%
Reasoning
Math
Complex Logic
Benchmark Scores
MMLU85.2
Code92.4
Chat88.1
$7.50/1M tokensAverage
Input$3.0
Output$12.0
Your cost$7.50

GPT-4 Turbo

Modelgpt-4-turbo
Context128K
SpeedUltra Fast
Perf88%
Legacy Support
Detailed Analysis
Benchmark Scores
MMLU86.4
Code87.1
Chat89
$20.00/1M tokensAverage
Input$10.0
Output$30.0
Your cost$20.00
Claude

Anthropic Claude

3 models • 1 recommended

Claude 3.5 Haiku

Modelclaude-3-5-haiku-20241022
Context200K
SpeedVery Fast
Perf76%
Cost Effective
Chat
Quick Tasks
Benchmark Scores
MMLU75.2
Code75
Chat78
$0.75/1M tokensAverage
Input$0.3
Output$1.3
Your cost$0.75

Claude 3.5 Sonnet

Rec
Modelclaude-3-5-sonnet-20241022
Context200K
SpeedFast
Perf91%
Coding
Writing
Analysis
Benchmark Scores
MMLU88.7
Code92
Chat90.8
$9.00/1M tokensAverage
Input$3.0
Output$15.0
Your cost$9.00

Claude 3 Opus

Modelclaude-3-opus-20240229
Context200K
SpeedUltra Fast
Perf88%
Complex Reasoning
Long Documents
Benchmark Scores
MMLU86.8
Code84.9
Chat91
$45.00/1M tokensAverage
Input$15.0
Output$75.0
Your cost$45.00
Gemini

Google Gemini

3 models • 1 recommended

Gemini 2.0 Flash-Lite

Modelgemini-2.0-flash-lite
Context1M
SpeedVery Fast
Perf75%
Ultra Budget
High Volume
Benchmark Scores
MMLU78
Code68
Chat79.5
$0.08/1M tokensAverage
Input$0.0
Output$0.1
Your cost$0.08

Gemini 2.0 Flash

Rec
Modelgemini-2.0-flash
Context1M
SpeedFast
Perf81%
Fastest
Cost Effective
Real-time
Benchmark Scores
MMLU83.5
Code74.3
Chat84
$0.19/1M tokensAverage
Input$0.1
Output$0.3
Your cost$0.19

Gemini 1.5 Pro

Modelgemini-1.5-pro
Context2M
SpeedUltra Fast
Perf82%
Long Documents
Analysis
Multimodal
Benchmark Scores
MMLU85.9
Code71.9
Chat87.2
$3.13/1M tokensAverage
Input$1.3
Output$5.0
Your cost$3.13
Grok

X.AI Grok

2 models • 1 recommended

Grok 2 Mini

Beta
Modelgrok-2-mini
Context128K
SpeedVery Fast
Perf69%
Cost Effective
Quick Tasks
Benchmark Scores
MMLU72
Code60
Chat74
$4.00/1M tokensAverage
Input$2.0
Output$6.0
Your cost$4.00

Grok 2

Rec
Beta
Modelgrok-2
Context128K
SpeedFast
Perf76%
Real-time Data
X/Twitter
Current Events
Benchmark Scores
MMLU79
Code68.5
Chat80
$10.00/1M tokensAverage
Input$5.0
Output$15.0
Your cost$10.00

Model Selection Tips

Cost Optimization

Use cheaper models for simple tasks like classification and summaries. Reserve premium models for complex reasoning and creative work.

Context Matters

Match context window to your needs. Larger contexts cost more but handle longer documents. Most tasks work well with 8-32k tokens.

Speed vs Quality

Faster models are great for real-time applications. Use slower, more capable models for accuracy-critical tasks.

Ready to Start Tracking Your AI Costs?

Connect your providers and get instant insights into your AI spending