ModelsGPT-5.6 Luna Pro: A Request Setting Sold as a Model Name
GPT-5.6 Luna Pro is Luna with reasoning mode set to pro, billed at Luna's own token rates. How pro mode bills, how it differs from effort, and how to test it.
ReadNotes on models, agents, and what inference costs
Practical writing for developers building with large language models — how they work, how to pick one, and how to keep the bill predictable.
Models
ModelsGPT-5.6 Sol Guide: The July Flagship, Three Generations Later
GPT-5.6 Sol brought max effort, pro mode and persisted reasoning in July 2026. Its price, latency, GDPval result, and whether GPT-6 Sol has made it redundant.
ReadModelsGPT-5.6 Sol Pro: When Pro Mode Is Worth the Wait
Sol Pro is GPT-5.6 Sol with reasoning.mode set to pro: same weights, same token rates, more tokens per answer. How it bills, how to call it, and when it pays.
Read
ModelsGPT-5.6 Terra Pro: Spend Tokens Before You Upgrade Tiers
Terra Pro is GPT-5.6 Terra with pro reasoning mode on. When paying for more work on the cheaper model beats moving up to Sol, and how to measure the difference.
Read
ModelsGPT-5.6 Terra: The Middle Tier and Its 272K Pricing Cliff
GPT-5.6 Terra costs half of Sol per token with the same 1M window, tools and effort levels. Where it fits, how the long-prompt surcharge works, and when to step up.
Read
ModelsGPT-6 Astra Guide: OpenAI's Flagship, Priced Per Task
GPT-6 Astra lists at $10 in and $50 out per million tokens with a 1M window. What changed in behaviour, the new API features, and when Sol is the better default.
Read
ModelsGPT-6 Astra Pro: When Pro Mode Is Worth Astra Prices
GPT-6 Astra Pro is not a bigger model. It is Astra with pro reasoning mode switched on, billed at Astra rates for more tokens. When that trade pays, and when it does not.
ReadModelsGPT-6 Luna Guide: OpenAI's Cheapest GPT-6 Tier in Practice
GPT-6 Luna lists at $0.10 in and $0.50 out per million tokens with a 1M window. What it is for, where the long-context tier bites, and when to step up to Sol.
ReadModelsGPT-6 Luna Pro: Buying Depth Without Moving Up a Tier
GPT-6 Luna Pro runs Luna in pro reasoning mode at Luna's own rates. How it differs from raising effort, when it beats stepping up to Sol, and how to measure it.
ReadModelsGPT-6 Sol Pro: The Mid-Tier Escalation Before Astra
GPT-6 Sol Pro is GPT-6 Sol in pro reasoning mode at Sol's rates. How pro mode differs from effort, how it compares with Astra, and where its latency is acceptable.
ReadModelsGPT-6 Sol: What Changed From GPT-5.6 Sol, and What Did Not
GPT-6 Sol halved the GPT-5.6 Sol price and claims fewer mistakes. What OpenAI actually published, how Sol compares with Astra, and why 6.1 Sol already matters.
ReadModelsGPT-6.1 Sol Guide: OpenAI's Middle Tier at a Fifth of Astra's Price
GPT-6.1 Sol is OpenAI's middle GPT-6 model at $2 in and $10 out per million tokens. The migration traps, the 272K price cliff, and how to test it against Astra.
ReadShowing 121–132 of 731 articles