Cost Comparison of Models Per Task

Scobleizer · x · 2026-07-20

The post shares a comparison table showing the cost per "index task" across various models, covering Claude, Mistral, Qwen, GPT, Gemini, GLM, Kimi, DeepSeek, and others.

The table outlines a cost range from $2.75 down to $0.02. The cheapest is DeepSeek V4 Flash ($0.02), followed by models like MiMo-V2.5-Pro ($0.03), DeepSeek V4 Pro ($0.04), and gpt-ass-120b ($0.06). The original post concludes by asking readers which model they use most frequently.

Related event: Benchmark Compares LLMs on Cost-Efficiency and Deep Context Understanding(4 posts)→

Original post →

More from Models

Models channel →