Pricing & Models

Pricing & Models: Rate cards, tokenizers, tiers, and the cliffs between them. 42 field notes from the engineers shipping Nadir's LLM routing layer.

Posts in Pricing & Models

• Seven Dates, One Bill (2026-10-28)
• Which Cut Was Yours? (2026-10-26)
• Codex Credits by Model: Astra Costs 100x Luna per Turn (2026-10-22)
• Own the Base, Rent the Peak (2026-10-21)
• The Replacement Is a Raise (2026-10-17)
• The Flat Quarter (2026-10-15)
• The Price of a Second (2026-10-11)
• The Ten-Cent Haiku (2026-10-08)
• Cheaper on Paper (2026-10-06)
• Same Weights, Different Model (2026-10-03)
• Three at $2/$10 (2026-10-02)
• More Than Plus (2026-09-28)
• GPT-6 API Pricing: Luna, Terra, Sol and Astra Compared (2026-09-23)
• Fable 5.1 vs GPT-6 Astra: Same Price, 57% Apart (2026-09-23)
• LLM API Pricing, November 2026: The Complete Comparison (2026-09-23)
• Rush Hour (2026-09-21)
• Flash Frozen (2026-09-20)
• Two Autos, One Bill (2026-09-17)
• The Watt Wall (2026-09-14)
• The Reasoning Premium (2026-09-07)
• The MoE Mirage (2026-09-05)
• The $1.16 Floor (2026-08-31)
• The Cliff That Didn't Happen (2026-08-27)
• Four Prices, One Model (2026-08-25)
• The 200K Line (2026-08-14)
• The Two-Speed Market (2026-08-10)
• The Floor Just Moved (2026-08-09)
• The Rate Card Trap (2026-08-06)
• Fewer Tokens, Bigger Bill (2026-08-03)
• The 272K Cliff (2026-07-23)
• The Overthinking Tax (2026-07-22)
• Three Providers, Same 72 Hours (2026-07-21)
• The Multilingual Token Tax (2026-07-17)
• The Real Monthly Bill (2026-07-16)
• Self-Hosted LLM Cost per Token: Up to 36x Higher at Low Load (2026-07-16)
• Faster Isn't Cheaper (2026-07-05)
• A 4K Image Costs 10,764 Tokens (2026-07-01)
• The Thinking Bill (2026-06-18)
• Half Price, One Day Late (2026-06-12)
• Your API Price Can Change (2026-06-08)
• One Seventh the Price (2026-05-18)
• The Price Held. The Bill Didn't. (2026-05-11)

Pages on this site

• Home
• Pricing
• Nadir Lens
• Benchmarks
• Techniques
• What is an LLM router?
• AI gateway vs model router
• Savings calculator
• Solutions
• Routing
• Provider fallback
• Analytics
• Prompt clustering
• Compare
• Nadir vs LiteLLM
• Nadir vs OpenRouter
• Nadir vs Requesty
• Nadir vs Ramp Router
• Nadir vs Not Diamond
• Nadir vs Weave Router
• Nadir vs Portkey
• Contact
• Self-host with NadirClaw
• On-prem
• Context Optimize
• Docs
• Blog
• Agent skill
• Claude Code receipt
• Coding agents
• Cookbooks
• FAQ
• How it works
• Terms of Service
• Privacy Policy
• Data Processing Agreement
• Security

Machine-readable summaries of this site: llms.txt and llms-full.txt.