Routin is an OpenAI-compatible AI API gateway that helps developers access multiple model providers through one API, with routing, usage analytics and transparent billing.

Which AI model families can teams compare on Routin?

Routin highlights current model families such as GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, Claude Fable 5, claude-fable-5, GPT-5.5, GPT-5.4 mini, Claude Opus 4.8, Claude Sonnet 5, Gemini 3.5 Flash, Gemini 3.1 Pro Preview, DeepSeek Reasoner, Qwen3.7 Max, Grok 4.3, Mistral Medium 3.5, Mistral OCR 4 and other OpenAI-compatible chat, reasoning, image, audio, video and embedding models.

Can Routin work with OpenAI-compatible SDKs and coding agents?

Yes. Routin is designed for OpenAI-compatible integrations, including OpenAI SDK based apps, Codex, Claude Code, Cursor, Cline and other developer tools that can use a custom base URL and API key.

Does Routin show AI API pricing and context windows?

The public model catalog includes model provider metadata, pricing units, context windows, model types and token-based billing information where available.

What is the sora-2 API used for?

sora-2 is listed on Routin as a video. Developers can evaluate its provider, context window, pricing fields and OpenAI-compatible access for production AI apps and agents.

sora-2 is associated with OpenAI in the Routin model catalog when provider metadata is available.

How do I call sora-2 with an OpenAI-compatible client?

Create a Routin API key, set your OpenAI-compatible client base URL to the Routin API endpoint, and use sora-2 as the model name when making chat, response or modality-specific requests supported by the model.

How is sora-2 pricing evaluated?

Routin surfaces available pricing metadata for sora-2, including input price, billing unit, context tiers and cache-related prices when the provider exposes them.

<Back to Models

video

OpenAI

sora-2

Sora 2 is OpenAI's latest video and audio generation model, capable of directly outputting movie-level realistic videos based on text prompts. It features complete audio-visual capabilities such as multi-camera narrative, environmental and physical simulation, and synchronized sound effects. Users can also inject their own appearance and voice into characters through selfies or voice recordings, enabling "everyone to act in movies". In terms of real-world simulation, Sora 2 can precisely reproduce natural phenomena such as water, fabric, and gravity by following the laws of object movement, material properties, light and shadow, and dynamics, making character and camera movements highly credible.