Overview
This analysis examines LLM models with tool-calling capabilities - essential for agentic AI systems, MCP (Model Context Protocol) implementations, and multi-tool orchestration. Models are evaluated across two key dimensions:
- Cost per token - Economic efficiency for production use
- Context window size - Capability for complex, long-form tasks
Methodology
Quadrant Classification: Models are categorized into four quadrants based on median values calculated from the dataset:
- Cost Division: Median average cost (mean of input + output pricing) = calculated from data
- Context Division: Median context window size = calculated from data
This creates four categories: Low Cost/High Context, High Cost/High Context, Low Cost/Low Context, and High Cost/Low Context.
Attribution & Data Notes
- Data Collection: Daniel Rosehill
- Collection Date: November 8, 2025
- Source: Prices derived from API calls to OpenRouter
- Pricing Variability: OpenRouter pricing can fluctuate slightly according to the end inference provider. The same models may have slightly different pricing even at the time of capture.
- Data Exclusions: Free models (cost = $0) were excluded from this analysis
Data Notes
- Cost Calculation: Input and output pricing shown separately (per million tokens)
- Data Exclusions: Free models (cost = $0) were excluded from this analysis
- Color Coding: Cells are color-coded by tier - see legend below for ranges
All Models - Comprehensive View
Complete dataset with color-coded cost and context tiers. Click column headers to sort.
Cost Tiers ($/M tokens)
Context Window Tiers
| Model Name | Vendor | Context | Input ($/M) | Output ($/M) | Out/In Multiple | Quadrant |
|---|
Quadrant Analysis
- Overview: Models divided into four quadrants based on median cost and context values
- Green (Low Cost / High Context): Best value - low prices with large context windows
- Blue (High Cost / High Context): Premium models with extensive context capabilities
- Orange (Low Cost / Low Context): Budget-friendly for simple tasks
- Red (High Cost / Low Context): Specialized models with limited context
All Quadrants Overview
Complete view showing all models across quadrants with median division lines.
Individual Quadrant Deep Dive
Detailed view of each quadrant's models for easier comparison within each category.
Low Cost / High Context
High Cost / High Context
Low Cost / Low Context
High Cost / Low Context
Analysis Notes
- Quadrant Divisions: Based on median values for cost and context window size
- Logarithmic Scale: Cost axis uses log scale to better visualize the wide price range
- Median Lines: Dashed lines show median cost and context values across all models
Cost vs Context Quadrant Analysis
Interactive scatter plot showing the relationship between pricing and context window size. Hover over points for detailed model information.