sora-2 · OpenAI
Sora-2 is the next-generation text-to-video model evolved from Sora, optimized for higher visual realism, stronger physical consistency, and longer temporal coherence. It delivers more stable character consistency, complex motion rendering, camera control, and narrative continuity, while supporting higher resolutions and minute-level video generation for film production, advertising, virtual content creation, and creative multimedia workflows.
Sora-2 is the next-generation text-to-video model evolved from Sora, optimized for higher visual realism, stronger physical consistency, and longer temporal coherence. It delivers more stable character consistency, complex motion rendering, camera control, and narrative continuity, while supporting higher resolutions and minute-level video generation for film production, advertising, virtual content creation, and creative multimedia workflows.
On AIHubMix, Sora 2 costs $2 per million input tokens and $2 per million output tokens.
Sora 2 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 sora-2 — no other code changes needed.
Sora 2 is developed by OpenAI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Sora 2 was released on October 6, 2025 by OpenAI.
GPT-6.1 Terra is OpenAI’s multimodal reasoning model, supporting text and image inputs…
GPT-Image-2.6 Flare is OpenAI’s image generation and editing model for posters, product…
GPT-Image-2.6 Sunburst is OpenAI’s image generation and editing model for visual work…
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…
Use Sora 2 via the AIHubMix unified API — one interface for every major LLM.