AI 导读
Ox Alpha 在发布后三天内处理 11.6T tokens，达到 OpenRouter 上一个最大模型发布规模的 2.6 倍。该模型上下文窗口为 1.05M tokens，面向持续运行的智能体任务，单次会话可承载远超普通对话的文本量。OpenRouter 称其当天用量有望接近 6T tokens，并可通过 ori 在编码智能体中以 stealth/ox-alpha 调用。
正文
Ox Alpha processed 11.6T tokens in three days, 2.6x OpenRouter's previous biggest model launch.
This kind of scale is only possible now, because of coding agents, where long contexts, retries, and repeated tool calls can massively multiply token consumption inside one task.
Ox Alpha has a 1.05M-token context window and is intended for sustained agentic work, so each session can carry far more text than ordinary chat.
Ox Alpha is on track to hit nearly 6 trillion tokens today. Try it now via ori in your coding agents: $ ori [your favorite harness] --model stealth/ox-alpha https://t.co/VaYiDzVfZT在 X 查看被引用的帖子
来源：@rohanpaul_ai · x.com