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 4.5DeepSeek V4 Pro 0423
Claude Haiku 4.5

Anthropic

DeepSeek V4 Pro 0423

DeepSeek

Pricing
Input $/1M$1.00$0.90
Output $/1M$5.00$1.50
Blended $/1M (3:1)$2.00$1.05
Cache read $/1M$0.10$0.25
Cache write $/1M$1.25—
Quality indices
Intelligence Index7.420.8
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,1101,223
Web apps—1,000
Full-stack—948
UI components1,0881,209
Data viz1,1201,198
SVG1,0151,128
3D1,0461,227
Game dev1,0811,215
Godot game dev—1,059
Code categories1,1001,226
ASCII art1,1231,131
Specs
Context window200K1.05M
Max output tokens64K393K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek