Unverified50% confidenceFactExact time
GPT-6 Luna automatically performs context compression (auto-compact) upon reaching the limit under its default configuration.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/8/2026
First Seen
Valid until: 1/6/2027
Sources
Related Entities
Related Claims
VerifiedGPT-5.6 Luna is the fast, low-cost version, targeting large-scale repetitive tasks such as bulk rewriting, content classification, customer service responses, and high-frequency API calls.76% similarUnverifiedGPT-6 Luna can handle almost all tasks previously done with GPT-5.6 Soul, including making PPTs, video editing with subtitles, creating covers, automated publishing workflows, complex Skill modifications, simple project development, and researching new technologies.73% similarUnverifiedGPT-5.6 adopts a layered model architecture, using SOE for default scenarios, Terra for cost-performance balance, and Luna for high-throughput heavy tasks.73% similarUnverifiedGPT-5.6 offers two advanced options: MAX mode (longer reasoning time) and AUTO mode (four agents processing in parallel).71% similarUnverifiedIt is recommended to add a local configuration file at the project level specifying the default model as GPT-6 Luna and setting the Model Context Window to 800,000, rather than configuring this globally so as to avoid rapidly depleting the quota of higher-priced models.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987341API
curl https://kongchang.com/api/v1/knowledge/claims/987341MCP
get_claim(id=987341)