OpenAI bumps GPT-6.1 Sol default context to 500k in Codex and Work
OpenAI just increased the default context length for GPT-6.1 Sol in Codex and Work from 272k to 500k tokens, an 80% jump. The change helps minimize context compactions during long sessions and retains finer nuances over time. OpenAI calls 500k the tested sweet spot for most workflows, though users can still manually override it up to the model's 1M maximum limit.
If you use AI to work across massive codebases or sprawling docs, there is nothing worse than the model quietly compressing your conversation and stripping out subtle details.
OpenAI just pushed an update to fix that. The default context window for GPT-6.1 Sol across its Codex and Work products has jumped from 272K to 500K tokens, roughly an 80% bump.
A new sweet spot without the extra fees
According to OpenAI, the jump is designed to curb context compactions and help the model retain nuanced project history over longer sessions.
Testing showed that 500K is the sweet spot for everyday workflows. If you need more room, the model still supports up to a 1M token ceiling, which users can manually set. Best of all, OpenAI reportedly is not charging extra long-context surcharges when drawing from standard subscriptions.
Why it matters
Context limits are the silent productivity killer for heavy coders. While vendors love bragging about 1M token ceilings, practical usability often breaks down when platforms aggressively summarize context in the background.
We think bumping the baseline to 500K without jacking up subscription fees is a savvy quality-of-life win. It keeps developers inside the Codex ecosystem by making complex, multi-file sessions actually reliable.
Sources (1)
- x.com(opens in a new tab)Originalx.com