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 5.2
Claude Haiku 4.5

Anthropic

GLM 5.2

Z.ai

Pricing
Input $/1M$1.00$0.818
Output $/1M$5.00$2.57
Blended $/1M (3:1)$2.00$1.26
Cache read $/1M$0.10$0.152
Cache write $/1M$1.25
Quality indices
Intelligence Index29.651.1
Coding Index43.968.8
Math Index
Agentic Index16.443.1
Speed & latency
Output speed (tok/s)
Time to first token
Time to first answer token
Design Arena (Elo)
Website1,1491,338
Web apps1,273
Full-stack1,289
Mobile apps1,237
Android native1,235
UI components1,1421,335
Data viz1,1601,310
SVG1,0721,252
3D1,1311,353
Game dev1,1551,350
Agentic game dev1,193
Godot game dev1,143
HTML slides1,204
Python→PPTX slides1,187
Code categories1,1481,341
ASCII art1,1821,217
Specs
Context window200K1.05M
Max output tokens64K131K
Input modalitiestext, image, filetext
TokenizerClaudeOther