Compare Models

← Back to Models

Compare language models side by side by context window, maximum output, modalities, reasoning support, tools, and token prices. Select for the workload you will run rather than one headline benchmark: coding agents, long-document analysis, low-latency chat, structured extraction, and multimodal tasks place different demands on a model.

Estimate both input and output volume, include caching or batch discounts only when your traffic pattern qualifies, and test quality on representative prompts. Context-window size does not guarantee reliable use of every token. Provider availability, model aliases, rate limits, and pricing can change, so use this comparison as a planning aid and verify current API documentation before production deployment.

SPECIFICATIONS
Context Window 1.0M 1.0M 256K 400K
Max Output 66K 128K
Reasoning
INPUT MODALITIES
Text
Image
Audio
Video
OUTPUT MODALITIES
Text
Image
Audio
CAPABILITIES
Streaming
Function Calling
Structured Outputs
Thinking
TOOLS
Web Search
Code Execution
Computer Use
Image Generation
PRICING (per 1M tokens)
Input $1.25 $3.00 $0.05
Output $5.00 $15.00 $0.40
Cached Input $0.31 $0.30 $0.01

💸 Cost Calculator

Gemini 3 Pro

💸Price Calculator
Input1.0M
$1.25
Output0.5M
$2.50
Total: $3.75
3.8Coffee
🥇
0.0Gold (g)
🍕
1.5Pizza
🐄
0.1%Cow
🎮
0.1%RTX 5090

Claude Sonnet 4.5

💸Price Calculator
Input1.0M
$3.00
Output0.5M
$7.50
Total: $10.50
10Coffee
🥇
0.1Gold (g)
🍕
4.2Pizza
🐄
0.3%Cow
🎮
0.4%RTX 5090

GPT-5 Nano

💸Price Calculator
Input1.0M
$0.05
Output0.5M
$0.20
Total: $0.25
0.2Coffee
🥇
0.0Gold (g)
🍕
0.1Pizza
🐄
0.0%Cow
🎮
0.0%RTX 5090