skip to content- 2026-02-01
|
GLM 4.7: Legacy Z.AI Model Guide
Legacy guide for Z.AI GLM 4.7. GLM-5.2 is now the current Z.AI coding-plan model; use this page for historical context and GLM-4.7 fallback routing.
- 2026-01-31
|
Kimi Code: K3 and K2.7 Coding Membership
Kimi Code membership, model aliases and quotas, with an October 13 update and preserved July 18 CLI setup and K3/K2.7 API evidence.
- 2026-01-30
|
Budget AI Models: Value Shortlist and Evidence
Shortlist MiMo V2.6 Flash, DeepSeek V4.1 Flash, GLM-5.3 and Luna for useful low-cost work, with dated evidence and an accepted-result checklist.
- 2026-01-30
|
Mid-Range LLM Comparison: Production Spend Band
Current mid-range model-routing guide: GLM-5.2, Kimi K3, Kimi K2.7 Code, MiniMax M3, Claude Sonnet 5, GPT-6 Luna, and deliberate premium escalation.
- 2026-01-30
|
Premium LLM Comparison: Opus 5.5, GPT-6, Fable
Compare Sonnet 5, Opus 5.5, GPT-6, Fable 5, and restricted models by access, evidence, practical role, and cost per accepted task.