Fetching from the wire…
01
02
03
04
05
06
07
08
Models2026-09-23 · source-backed
OpenAI's model page says the Responses API allows tools at any effort level, Chat Completions does not. The migration guide also says to replace prompt_cache_retention with prompt_cache_options.ttl, drop temperature, top_p and top_logprobs whenever effort isn't none, and move "minimal" effort to "low." Requests over 272K input tokens pay double the input rate. Move your endpoint before you turn reasoning on, or your tool calls stop working.
Each link below shares sources, entities, or timing with this story.
Published September 7, it puts OpenAI Codex in the agent picker with a copy-ready ~/.codex/config.toml panel pointing Codex CLI and Desktop at Manifest over the Responses API (GitHub). Two compatibility fixes make it work: Responses-API role: "developer" instruction messages f...
Every tool result round-tripping through the model is a tax you've been paying without noticing. OpenAI's Responses API now ships Programmatic Tool Calling. The model writes JavaScript that coordinates your tools. It calls them in parallel, loops over results, branches on cond...
GPT-5.6 Luna went to $0.20 input / $1.20 output per million tokens on July 30. That's an 80% cut. Terra dropped 20%. Luna's input now undercuts Gemini 3.1 Flash-Lite ($0.25/$1.50) and sits at one-fifth of Claude Haiku 4.5's $1 input. Simon Willison covered the announcement and...
Four frontier models. Five sealed engineering problems. The result everybody will quote is that Claude Fable 5 won. The result that should actually change how you work is buried three-quarters down the page. JuliaHub published an evaluation on July 30 running four frontier mod...
On July 9 the standalone Codex app merged into ChatGPT desktop for macOS and Windows, keeping a dedicated coding surface alongside Chat and Work modes, plus inline diff editing, side-panel PR review, faster Computer Use on GPT-5.6, and multi-repository projects. The tiering: S...
Released September 10, GPT-5.6 and later now default to the Responses API rather than chat completions. If your eval config pins response shapes for those models, the upgrade moves them. The release also adds providers for Claude Fable and Mythos 5.1, GPT-6 Astra, grok-4.6, Ge...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.