GPT-5.6 Sol stuck at 272K context window, Terra/Luna upgraded to 872K
torrestomas-3f · ghdev · 2026-08-18
User reports that after OpenAI's long-context rollout, GPT-5.6 Sol remains capped at a 272K context window, while Terra and Luna models on the same account have been upgraded to 872K. Testing indicates a server-side catalog metadata or entitlement issue, as manual cache overrides work temporarily but revert upon refresh.
More from Models
- Google Criticized: Gemini 3.7 Still Missing From Its Own Jules Agent a Week Later — brandon_galang · 2026-08-24
- Qwen 27B 3.8 low quantization tested: Q3 XXS works well locally — jeremyckahn · 2026-08-24
- Users notice significant quality shift in GPT-5.6 output — haider1 · 2026-08-24
- Ramp Stats: Anthropic Opus 4.8 and Sonnet 4.6 Lead Usage — vista8 · 2026-08-24
- Tencent Releases UI-Mate-27B, a Desktop GUI Agent Model — tencent · 2026-08-24
- ConvRot Quant joins llama-cpp: Q6 accuracy nears Q8 quality — giveen · 2026-08-24