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 V3
Claude Haiku 4.5

Anthropic

DeepSeek V3

DeepSeek

Pricing
Input $/1M$1.00$0.257
Output $/1M$5.00$1.03
Blended $/1M (3:1)$2.00$0.45
Cache read $/1M$0.10—
Cache write $/1M$1.25—
Quality indices
Intelligence Index7.4—
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,1101,108
UI components1,0881,081
Data viz1,1201,084
SVG1,015966
3D1,0461,061
Game dev1,0811,037
Code categories1,1001,093
ASCII art1,123—
Specs
Context window200K164K
Max output tokens64K16K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek