Making Predictions

Dynamic AI model orchestration and inference scaling

---

The Predict API analyzes your images, texts, or videos and tells you what's inside of them. The API will return a list of concepts with corresponding probabilities of how likely it is these concepts are contained within the image.

We recommend specifying the version_id parameter in your predict calls. If no version_id is specified, predictions will occur on the most recent version of the model. This helps when you want to run a specific version of your model in production while building other future versions of your model.

This is also true with Clarifai's pre-trained models, as we will update them to have new versions from time to time. Therefore using a specific version_id keeps your production environment stable.

📄️ Images

Make predictions on image inputs

📄️ Video

Make predictions on video inputs

📄️ Text

Make predictions on passages of texts

📄️ Large Language Models (LLMs)

Make predictions using LLMs

📄️ Audio

Make predictions on audio inputs

📄️ Multimodal-to-Text

Make multimodal-to-text predictions

📄️ Embeddings

Translate complex data into numerical vector representations

📄️ Prediction Parameters

Learn about model prediction parameters.

📄️ Multilingual Classification

Multilingual predictions