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 VL 8B Instruct
Claude Haiku 4.5

Anthropic

Qwen3 VL 8B Instruct

Alibaba (Qwen)

Pricing
Input $/1M$1.00$0.25
Output $/1M$5.00$0.75
Blended $/1M (3:1)$2.00$0.375
Cache read $/1M$0.10$0.12
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 window200K262K
Max output tokens64K236K
Input modalitiestext, image, fileimage, text
TokenizerClaudeQwen3