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: Testing LLMs on Relationship Understanding with 600k Tokens(6 posts)→
More from Models
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- One stray 'u' and Claude starts spelling like a Brit — cantrell · 2026-10-27
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27
- ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export — mhmazur · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27