FinOps guides on LLM and cloud pricing

Practical FinOps guides on LLM and cloud pricing: batch and cache economics, model selection, and what the published rate cards leave out. Every figure is recomputed from the catalogue at build time. Data snapshot: 2026-11-14.

• ARM against x86: what Graviton, Ampere and Axion save
  The ARM discount clouds advertise is a discount against Intel. This guide measures it at matched vCPU and memory, against Intel and against AMD.
• Batch API economics: when the -50% applies
  Batch APIs cut LLM token prices roughly in half, but only for async workloads and only where a batch rate is published. Worked examples, current prices.
• Vision, audio, agents: what each capability adds to the bill
  What image input, audio and tool use add to an LLM bill, measured within each model maker's line-up and across the catalogue, and the shortlist each leaves.
• Context windows: what a million tokens costs to fill
  A million-token context window is a spec-sheet capability and an invoice line. What one full prompt costs across the catalogue, and what re-reading it costs.
• The cost of reasoning: what thinking models charge for output
  Reasoning tokens are billed as output tokens, where prompt caching cannot reach them. What a thinking budget costs across the catalogue, at current prices.
• How we compute cost per request
  The exact formulas behind the list-price and after-discounts columns: token profiles, cache and batch rules, what the numbers exclude and where they mislead.
• How the models are scored: Arena quality, Efficiency, the FinOps badge and quality bars
  Where the quality score comes from, how the Efficiency score and the FinOps badge are calculated, and how a quality bar is set for a use case.
• LLM API pricing statistics: cheapest and median
  How many LLM APIs carry a token price, which are the cheapest and the dearest, and the median price per million tokens by tier and by licence. Rebuilt daily.
• Memory-optimised against general purpose: what a GB costs
  Memory-optimised instances cost more an hour and less per GB. This guide reads the price of one GB and one vCPU off each cloud's rate card, at matched sizes.
• Open weights against proprietary APIs: the cost gap in numbers
  Open-licensed models undercut proprietary APIs at matched quality across most of the range, but the open catalogue stops below the top tier. Live prices.
• Prompt caching: the discount nobody budgets for
  Cache reads bill at a fraction of the input price, but the saving that reaches the bill is far smaller than the headline. Break-even by use case, live prices.
• A quality bar for each use case, and the cheapest model that clears it
  Decide per use case how good the answer has to be, set the bar on Arena, then buy the cheapest model that clears it. A method, with current prices.
• Quality per dollar: the models that beat their price class
  A model's price class comes from its rate card, not its quality. Measured against Arena scores, most of the catalogue has a cheaper equal. Current prices.
• Savings plans against reserved instances: what the flexibility costs
  AWS and Azure each sell a flexible commitment and a locked one. What each takes off on-demand, the gap between the two and the utilisation where each pays off.
• Bedrock, Vertex, Azure or direct: what the channel changes
  The same model is sold by its model maker and by the hyperscalers. The token rate is identical on most comparisons; regions and commitment terms are not.