GPT-5.4
GPT-5.4 is an OpenAI reasoning model presented in the API & Codex Build Hour as a token-efficient coding and agent model with native computer-use capabilities.
Key facts
- Type: Reasoning / coding / computer-use model
- Maker: OpenAI
- Codex role: Presented as a major Codex model release and one of the models behind the shift from pair programming to agent delegation [src-084].
- Context length: OpenAI describes GPT-5.4 as supporting up to a million tokens of context [src-084].
- Computer use: The session describes native computer-use-agent capabilities and a new API surface for managing browsers and computers [src-084].
- Tool search: GPT-5.4 is paired with a tool search capability for progressively discovering tool namespaces instead of loading hundreds of tools into context at once [src-084].
- Efficiency: OpenAI frames it as a token-efficient reasoning model, matching strong coding performance with lower token consumption and latency than earlier Codex models [src-084].
Related
- See also: OpenAI, Codex (OpenAI), GPT 5.5
- Concepts: Agentic Engineering, Harness Engineering, Progressive Context Loading (Skills), Claude Code Token Economics
Source references
- [src-084] OpenAI Codex, Workspace Agents, Prompt Caching, and Superintelligence Policy cluster (2026-02-09 to 2026-05-08)
Recommended next
Keep reading from this thread
From 491 indexed pages and articles.
- Wiki concept OpenAI Workspace Agents Codex-powered agents in ChatGPT for shared team workflows that run in the cloud across files, apps, skills, schedules, Slack Related by 084
- Wiki concept Progressive Context Loading (Skills) The three-level loading pattern Claude Code uses to keep skills lightweight. Level 1: initial search only reads the YAML frontmatter (name + Related by loading
- Insight AI Beyond POCs How enterprise AI moves beyond proofs of concept through ownership, governance, measurement, adoption, and production operating models Readers have engaged with this next