Venice AI
OpenAI priced GPT-6.1 Sol at $2 per million input tokens, $0.10 per million cached input tokens, and $10 per million output tokens, matching GPT-6 Sol's uncached rates while cutting cached input pricing by 50%. This delivers near-flagship GPT-6 Astra capability at one-fifth of Astra's standard pricing for enterprise developers. Alongside the model, OpenAI introduced an Ultrafast inference tier reaching up to 300 tokens per second in the API and offering 8X faster generation in Codex, available immediately for GPT-6 Astra with GPT-6.1 Sol support coming soon. The premium tier costs 6X the standard API rate, placing OpenAI's frontier throughput above Gemini 3.5 Flash's 201 tps but below specialized speed models per Artificial Analysis.