AiCostCompare

Compare models

Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.

Claude Haiku 4.5GLM 5.1
Claude Haiku 4.5

Anthropic

GLM 5.1

Z.ai

Pricing
Input $/1M$1.00$0.966
Output $/1M$5.00$3.04
Blended $/1M (3:1)$2.00$1.48
Cache read $/1M$0.10$0.179
Cache write $/1M$1.25
Quality indices
Intelligence Index29.640.2
Coding Index43.955.8
Math Index
Agentic Index16.429.9
Speed & latency
Output speed (tok/s)
Time to first token
Time to first answer token
Design Arena (Elo)
Website1,1491,302
Web apps1,228
Full-stack1,225
Mobile apps1,225
Android native1,233
UI components1,1421,321
Data viz1,1601,366
SVG1,0721,267
3D1,1311,336
Game dev1,1551,328
Agentic game dev1,182
Godot game dev1,112
HTML slides1,200
PPTX slides1,241
Python→PPTX slides1,258
Agentic slides1,245
Agentic HTML slides1,205
Agentic slides (HTML)1,204
Agentic slides (Python PPTX)1,240
Code categories1,1481,311
ASCII art1,1821,182
Specs
Context window200K205K
Max output tokens64K128K
Input modalitiestext, image, filetext
TokenizerClaudeOther