o1 · OpenAI
OpenAI's most powerful O-series model supports official cache hits that halve the input cost.
OpenAI's most powerful O-series model supports official cache hits that halve the input cost.
On AIHubMix, O1 costs $15 per million input tokens and $60 per million output tokens. Cached input reads are billed at $7.5 per million tokens.
O1 accepts text input.
O1 supports thinking. Per-protocol parameter support is listed in the capability table on this page.
O1 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to o1 — no other code changes needed.
O1 is developed by OpenAI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
O1 was released on December 5, 2024 by OpenAI.
GPT-6.1 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for…
GPT-6 Luna is OpenAI's latest and most efficient model, designed for focused…
GPT-6 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for complex…
GPT-6 Astra is OpenAI's newest and most intelligent model, with industry-leading…
OpenAI's latest realtime speech-to-text model, built for low-latency use — it streams…
GPT-Realtime-2.1 is a reasoning speech-to-speech model for the Realtime API, with tool…
Use O1 via the AIHubMix unified API — one interface for every major LLM.