OpenAI's Codex lead Tibo says GPT-6.1 Sol's default context in Codex and ChatGPT Work goes from 272K to 500K (~80% more) to cut compactions on long tasks, with no long-context fees when usage comes from a ChatGPT subscription. Separately, the official Codex changelog says GPT-5.5 retires from ChatGPT and Codex on all plans on October 14 (the API keeps it).

Key Takeaways

  • ✓Default context 272K → 500K (~+80%) for GPT-6.1 Sol in Codex and ChatGPT Work; OpenAI says it will go higher later
  • ✓No long-context fees on subscription usage; on the API, prompts over 272K input tokens bill at 2x input and 1.5x output
  • ✓API GPT-6.1 Sol: 1,050,000-token context window, 128,000 max output, $2 / $10 per 1M tokens standard
  • ✓Override with model_context_window and model_auto_compact_token_limit in ~/.codex/config.toml
  • ✓GPT-5.5 retires from ChatGPT and Codex on all plans on Oct 14; the API keeps it
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
Default context 272K → 500K (+80%) for GPT-6.1 Sol in Codex and ChatGPT Work; OpenAI says it will go higher later
Full Leaderboard→
💰 Cost & PlansCompare
in: $2 / out: $10
Compare Plans↗
🛠️ Ecosystem & IDERules
Codex · GPT-6.1 Sol · OpenAI
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
🔗

Project Links & Resources

Direct Access
Direct access to official project resources and documentation
📖
GPT-6.1 Sol model page (context, pricing)
developers.openai.com/api/docs/models/gpt-6.1-sol
↗
📖
Codex changelog (GPT-5.5 retirement Oct 14)
developers.openai.com/codex/changelog
↗
📖
Codex configuration reference
developers.openai.com/codex/config-reference
↗
📖
Codex pricing and credits
developers.openai.com/codex/pricing
↗
🔬

In-Depth Technical Analysis

On day 7 of Codex's 28-day improvement series, Codex lead Tibo announced that GPT-6.1 Sol's default context in Codex and ChatGPT Work rises from 272K to 500K tokens (about 80% more), aimed at fewer compactions on long tasks, with more to come. This changes the default, not the model: per OpenAI's model page, GPT-6.1 Sol supports a 1,050,000-token context and 128,000 max output on the API, where prompts above 272K input tokens are billed at 2x input and 1.5x output. Tibo says subscription usage carries no long-context fees. OpenAI published no benchmarks for the change. Users can override defaults via model_context_window and model_auto_compact_token_limit in ~/.codex/config.toml. Separately, the official Codex changelog says GPT-5.5 retires from ChatGPT, ChatGPT Work and Codex on all plans on October 14, 2026; the API keeps it.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗