Codex workflows on Amazon Bedrock with GPT‑5.6 Sol can see major cost spikes when explicit prompt cache controls aren’t sent. Cache writes cost 1.25×, while reads get a 90% discount—so missing cache breakpoints turns caching into churn instead of reuse.
OpenRouter lists GPT‑5.6 Sol at $2.50/1M input tokens and $15/1M output tokens during a 50% promotion, with 1M context and a Feb 2026 knowledge cutoff. ([openrouter.ai](https://openrouter.ai/openai/gpt-5.6-sol)) Real-world bills depend on provider routing and caching (fresh vs cached reads), which can shift your effective cost.
GPT‑5.6 Luna and Terra are cheaper, and GPT‑5.6 Sol adds Fast mode for lower latency. This post breaks down how token pricing, prompt caching, and inference/agent efficiency combine for better AI ROI in real workloads.
GPT‑5.6 is a model family (Sol, Terra, Luna) built for more useful work per token, with controllable reasoning effort and an Ultra-style multi-agent option. It also introduces Programmatic Tool Calling to reduce wasted intermediate tool output and accelerate complex workflows.