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 4.5Qwen3.5 397B A17B
Claude Haiku 4.5

Anthropic

Qwen3.5 397B A17B

Alibaba (Qwen)

Pricing
Input $/1M$1.00$0.45
Output $/1M$5.00$3.00
Blended $/1M (3:1)$2.00$1.09
Cache read $/1M$0.10$0.22
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)
Website1,1101,179
UI components1,0881,151
Data viz1,1201,170
SVG1,0151,129
3D1,0461,135
Game dev1,0811,124
Code categories1,1001,165
ASCII art1,123—
Specs
Context window200K262K
Max output tokens64K82K
Input modalitiestext, image, filetext, image, video
TokenizerClaudeQwen3