search
Decisions API
Trends
- 1OpenRouter's 5.5% fee prompts cost comparison with self-hosting●OpenRouter's fee is 5.5% at the credit door, not per-token markup. Honest math on gateway vs direct vs self-hosted LiteL
Developers are debating OpenRouter's pricing model, noting the service charges a 5.5% fee when users add credits rather than a per-token markup on API calls. A breakdown compares the total cost of routing AI requests through OpenRouter versus paying providers directly or self-hosting an open-source proxy like LiteLLM, offering a decision rule for choosing between the three approaches.
Repos
- firelex/jeff Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrate
- jaredpalmer/kev Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
- ollaya-dev/ollaya Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollam
- Contrastive-LM/CLM
- jev-chat/jev-chat-jarvis 装在手机上的对话副驾：在 QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框，发不发由你。非侵入，只读屏幕，不 hook 不改包。
- Rizzo-AI-Academy/rizzo-flow The open, local take on Jev: typed decisions from an LLM, without generating a single token
- tamaratran/fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one
- mizorewww/laya-mlx Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or c
- PostHog/jeeves Jeeves – Reasoning improves Jev-like decision models
- mizorewww/laya-coreml Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reprodu
- githubnext/localjev