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.

GPT-5.6 SolQwen2.5 VL 72B Instruct
GPT-5.6 Sol

OpenAI

Qwen2.5 VL 72B Instruct

Alibaba (Qwen)

Pricing
Input $/1M$4.00$0.80
Output $/1M$20.00$1.00
Blended $/1M (3:1)$8.00$0.85
Cache read $/1M$0.40$0.40
Cache write $/1M$5.00—
Quality indices
Intelligence Index——
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Specs
Context window1.05M128K
Max output tokens128K115K
Input modalitiesfile, image, texttext, image
TokenizerGPTQwen