OpenAI's Decisions API now takes image input — one creator picks YT thumbnails for $0.13
stevenheidel · x · 2026-10-07
OpenAI engineer Steven Heidel announced that the Decisions API now supports image input. Developer Claire Vo demonstrated a real use case: using the cheap model ($0.13 per run) to pick her best face from 40 minutes of footage and generate YouTube thumbnails automatically. Vision-enabled decision calls open up low-cost batch image screening and selection workflows for creators.
More from coding & agent
- 55,000 Lines From One Prompt: Matt Shumer Open-Sources the Gauntlet Loop Method — letandrewcook · 2026-10-07
- Developer uses Opus 5.5 to recreate seven Adobe apps including Photoshop as free open-source Rust alternatives — kimmonismus · 2026-10-07
- Adding t_wada's commenting principles to AGENTS.md slashed noisy AI code comments — 4310sy · 2026-10-07
- openTPU: A One-Person Open-Source AI Accelerator Designed by AI Agents, Running 10 LLMs on an FPGA — ai · 2026-10-07
- Agent workflows don't matter — your log of traces for training future orchestrators is what compounds — natesiggard · 2026-10-07
- "Fix your failing self until the task completes": a developer's go-to Codex prompt — jdjohnson · 2026-10-07