GPT-5.6 Goes GA: Programmatic Tool Calling Changes Everything

OpenAI released GPT-5.6 with three tiers (Sol, Terra, Luna) and a new Programmatic Tool Calling feature that lets agents write and execute lightweight programs between tool calls, reducing token usage and latency. Ploy.ai reported cost savings of $2.22 per build versus $3.06 and faster completion times after migrating from Claude Opus 4.8 to GPT-5.6 Sol.

GPT-5.6 went GA with three tiers Sol, Terra, Luna and a new capability that matters more than the benchmarks: Programmatic Tool Calling . Agents can now write and execute lightweight programs between tool calls — filtering data, coordinating tools, monitoring progress — without round-tripping intermediate results through the context window. Fewer tokens, fewer model calls, faster task completion. Production receipts: Ploy.ai migrated from Claude Opus 4.8 to GPT-5.6 Sol. Results: $2.22 per build vs $3.06. Half the wall-clock time. Also in this issue: 📬 Read the full issue: https://theagenticengineer.waltsoft.net/archive/gpt-56-goes-ga-programmatic-tool-calling-changes-e https://theagenticengineer.waltsoft.net/archive/gpt-56-goes-ga-programmatic-tool-calling-changes-e This is Issue 21 of The Agentic Engineer — a weekly newsletter for developers building with AI agents.