Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.bettertoken.ai/llms.txt

Use this file to discover all available pages before exploring further.

Release date: April 24, 2026 BetterToken has updated the GPT-5.5 model entry. Check the model plaza for the currently available Codex group model ID, then configure it in Codex, OpenCode, OpenClaw, Cursor, Cline, Zed, or other external tools through the matching setup guide. OpenAI officially introduced GPT-5.5 on April 23, 2026 and described it as a model for complex real-world work. OpenAI highlights stronger agentic coding, computer use, knowledge work, and scientific research workflows. It is designed to understand intent earlier, plan more effectively, use tools, check results, and continue through multi-step tasks.

​
Highlights

  • Stronger coding-agent performance: OpenAI reports improvements over GPT-5.4 on coding and agentic benchmarks such as Terminal-Bench 2.0 and SWE-Bench Pro
  • More reliable long tasks: It is better suited for workflows that combine implementation, debugging, validation, and documentation
  • More active tool use: OpenAI emphasizes stronger tool use, output checking, and progress through ambiguous tasks
  • Higher efficiency: OpenAI says GPT-5.5 keeps GPT-5.4-level latency while using fewer tokens on Codex tasks

​
Setup guidance

For Codex and external tools, copy the current Codex group model ID from the model plaza. Do not hardcode a model name that is not shown there. If your Codex version cannot select gpt-5.5 in API mode, see Why can’t Codex use GPT-5.5 in API mode?.

​
Official sources