Dev shares OpenRouter stats: MiniMax serves 30M tokens per $1 at Intelligence Index 57
MaziyarPanahi · x · 2026-09-04
Developer MaziyarPanahi shared his raw OpenRouter usage data, surprised by how much he'd been using MiniMax models. His cost-efficiency comparison:
- MiniMax: 30M tokens per $1, Intelligence Index 57
- Gemini 3.8 Flash: index 59, but the same $1 bought only 5M tokens
- GLM-5.3 Flash: 2 points behind, yet 6× more tokens for the same price
- All via OpenRouter with the same cap and 96% cache rate
His verdict: cheap intelligence is getting ridiculous.
More from Models
- LangSmith data: gpt-4o-mini reaches 13% of orgs; DeepSeek V4 Flash is the only open-weight model on the lists — LangChain · 2026-09-04
- Polymarket puts 60% odds on next Claude Opus releasing by end of September — Polymarket · 2026-09-04
- Gemini 3.8 Flash Lands on Netlify AI Gateway Day One: Zero Config, No Keys, Built-in Caching — thisiskp_ · 2026-09-04
- DLSS 5 looks 'crazy good' as NVIDIA's AI upscaling impresses users — ssh4net · 2026-09-04
- Dev's accidental A/B test: reverting from .8 to .6 reveals dramatic capability gap — AI_Andrew · 2026-09-04
- GPT-6 Astra one day old: 12 community showcases from house modeling to game-style scenes — iamfakhrealam · 2026-09-04