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 4.5Qwen2.5 Coder 32B Instruct
Claude Haiku 4.5

Anthropic

Qwen2.5 Coder 32B Instruct

Alibaba (Qwen)

Pricing
Input $/1M$1.00$0.66
Output $/1M$5.00$1.00
Blended $/1M (3:1)$2.00$0.745
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)
Website1,110—
UI components1,088—
Data viz1,120—
SVG1,015—
3D1,046—
Game dev1,081—
Code categories1,100—
ASCII art1,123—
Specs
Context window200K33K
Max output tokens64K29K
Input modalitiestext, image, filetext
TokenizerClaudeQwen