Teknium: avoid 900k GPT variants — they charge extra beyond 272k context
Teknium · x · 2026-11-16
Responding to a Hermes Ultra subscriber complaining about fast usage burn, Nous Research's Teknium advises avoiding the 900k variants of GPT models, which incur extra charges beyond 272k context. He also says cache warning optimizations are coming soon that should save on all models.
Related event: Nous' Teknium Warns Against GPT 900k Variant Over Extra Billing(3 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16