If you copy a "config.toml" from a Codex tutorial written in the spring and try to launch Codex, it may not start at all. For ...

Imagine this: you’re working on a project that requires an AI agent to not only understand complex instructions but also interact seamlessly with tools, maintain context, and deliver reliable outputs.

OpenAI launched its Decisions API at DevDay 2026, using a specialized GPT-6 Luna model to make fast, constrained choices with ~150ms latency.

OpenAI's API now lists aurora-red-alpha, aurora-green-alpha and aurora-blue-alpha models with no documentation or official ...

OpenAI’s Decisions API enters public beta, returning typed answers about 10x faster at $0.10 per 1M input tokens.

OGX is plainly described as: an open-source agentic API server for building AI applications, OpenAI-compatible, any model, any infrastructure. It is the rebrand of Meta's Llama Stack, with the name ...

At Luna’s prices, routine extraction and summarization can be pushed toward a much cheaper tier. Sol targets recurring coding and agent work at Sonnet-class token pricing. Astra remains available for ...

OpenAI is bringing o1, its “reasoning” AI model, to its API — but only for certain developers, to start. Starting Tuesday, o1 will begin rolling out to devs in OpenAI’s “tier 5” usage category, the ...

OpenAI’s GPT-Live-1 adds full-duplex voice, faster turn-taking, and tool use for developers building real-time AI agents and customer workflows. OpenAI’s new voice model takes situational awareness ...

OpenAI’s end of the year event is here. The company is hosting “12 Days of OpenAI,” a series of daily… The Disrupt experience is meant to be shared. Get your pass and bring a colleague, partner, or ...

Usage API monitors token usage by minute, hour, or day and includes a costs endpoint that provides a breakdown of daily spend. OpenAI has introduced the Usage API, an API that allows enterprises to ...