ALEX THORPEAI PM
Online
LLM index · $ per 1M tokens · 339 models · median out $1.60 · OpenRouter 2026-10-2922d agoCLAUDE HAIKU 5.5$0.10 IN / $0.50 OUT1M ctx▼ 0.3× med58d agoCLAUDE FABLE 5.1$10 IN / $50 OUT1M ctx▲ 31.3× medNew3d agoGPT-6.1 TERRA PRO$1.00 IN / $5.00 OUT1.1M ctx▲ 3.1× med6mo agoGPT-5.5 PRO$30 IN / $180 OUT1.1M ctx▲ 112.5× medNew16d agoGEMINI 4 ARGON$2.00 IN / $10 OUT1M ctx▲ 6.3× med57d agoGEMINI 3.8 FLASH$0.83 IN / $4.13 OUT1M ctx▲ 2.6× med38d agoGROK 4.7$2.00 IN / $6.00 OUT500K ctx▲ 3.8× med3mo agoGROK 4.6$2.00 IN / $6.00 OUT500K ctx▲ 3.8× medNew14d agoMUSE SPARK OPEN$1.25 IN / $4.25 OUT1M ctx▲ 2.7× medNew17d agoMUSE WONDER$4.00 IN / $20 OUT1M ctx▲ 12.5× med49d agoDEEPSEEK V4.1 FLASH$0.04 IN / $0.50 OUT1M ctx▼ 0.3× med6mo agoDEEPSEEK V4 PRO 0423$0.89 IN / $1.79 OUT1M ctx▲ 1.1× med36d agoQWEN3.8 MAX PRIME$4.00 IN / $12 OUT1M ctx▲ 7.5× med38d agoQWEN3.8 OMNI FLASH$0.15 IN / $0.47 OUT1M ctx▼ 0.3× med23d agoMISTRAL LARGE 4$1.36 IN / $4.18 OUT1M ctx▲ 2.6× med6mo agoMISTRAL MEDIUM 3.5$1.50 IN / $7.50 OUT262K ctx▲ 4.7× medNew6d agoKIMI K3.1 PRO$2.00 IN / $10 OUT1M ctx▲ 6.3× med3mo agoKIMI K3$0.24 IN / $11 OUT1M ctx▲ 6.8× medNew10d agoMINIMAX M3.1 FLASH$0.15 IN / $0.60 OUT1M ctx▼ 0.4× med5mo agoMINIMAX M3$0.30 IN / $1.20 OUT1M ctx▼ 0.8× medNew14d agoNEMOTRON 3.5 SUPER VL$0.15 IN / $0.50 OUT1M ctx▼ 0.3× med5mo agoNEMOTRON 3 ULTRA$0.60 IN / $2.40 OUT262K ctx▲ 1.5× med

Writing  /  3 essays

Experiments

Small tools and working examples: LLM evaluation in Python, AI-assisted research, and lessons from testing ideas in code.

  1. 001How I Evaluated an MCP Server for a Headless Enterprise PlatformAI Agents2026.10.29 · 4′
  2. 002Scaling Qualitative Research with AIexperiments2025.12.09 · 3′
  3. 003LLM-Expect: Testing LLM Functions in Pythonexperiments2025.11.24 · 3′