GPT-5.4 and GPT-5.4 Pro released, with tool search and a 1M-token context window

Released GPT-5.4, our newest frontier model for professional work, to the Chat Completions and Responses API, and released GPT-5.4 Pro to the Responses API for tougher problems that benefit from more compute.

Also released:

• Tool search in the Responses API, which lets models defer large tool surfaces until runtime to reduce token usage, preserve cache performance, and improve latency.
• Built-in Computer use support in GPT-5.4 through the Responses API computer tool for screenshot-based UI interaction.
• A 1M token context window and native Compaction support for longer-running agent workflows.