Models Overview

A third-party open source text model from Z.ai with a 1M-token context window.

Our frontier-class multimodal model optimized for agentic and coding use cases.

Hybrid model unifying instruct, reasoning, and coding in a single efficient model.

A state-of-the-art, open-weight, general-purpose multimodal model.

A powerful model offering best-in-class text and vision capabilities.

A powerful and efficient model offering best-in-class text and vision capabilities.

A tiny and efficient model offering best-in-class text and vision capabilities.

Our latest OCR service with paragraph-level bounding boxes and structural block labels.

Our OCR service powering our Document AI stack. OCR 4 is available as the newer model. OCR 3 remains available for existing integrations and production workloads.

State-of-the-art TTS with zero-shot voice cloning and multilingual support.

An efficient audio input model, pre-trained and optimized for transcription purposes.

An efficient audio input model, pre-trained and optimized for live transcription purposes.

Our first model with audio input capabilities for instruct use cases.

Our cutting-edge language model for code completion released end of July 2025.

Our state-of-the-art semantic for extracting representation of code extracts

Our state-of-the-art semantic for extracting representation of code extracts

Compact multimodal moderation model for text and image safety classification.

Our latest moderation model with 128k context window and jailbreaking detection.

Updated code agent for Lean 4 formal proof engineering and automated theorem proving.