OpenAI Boosts GPT-6 Default Speeds by ~50%

OpenAI has raised default inference speeds for GPT-6 Astra and GPT-6.1 Sol by about 50% to roughly 50 tokens per second via subscription channels, with users confirming the jump from 30 tokens per second.

2026-10-06 ~ 2026-10-06 · 2 related posts

• OpenAI boosts default GPT-6 Astra and GPT-6.1 Sol speed ~50% to 50 tokens/sec — kimmonismus · 2026-10-06
• Claim: GPT-6-Astra and GPT-6.1 Sol now hit 50 tokens per second — kimmonismus · 2026-10-06