Sapiens AI Models

Agnes-Video-V2.0 is a next-generation cinematic video generation model designed for high-quality text-to-video, image-to-video, multi-image video generation, and keyframe animation workflows. It generates high-fidelity videos with strong motion consistency, scene coherence, and visual realism, enabling users to create production-ready video content from text prompts, reference images, or multiple keyframes. Agnes-Video-V2.0 is suitable for storytelling, marketing videos, product demos, social media content, immersive visual production, and AI-powered creative workflows.

Agnes Image 2.1 Flash is an upgraded image generation model optimized for high-information-density visuals, complex compositions, and rich semantic detail. It supports text-to-image generation, image-to-image editing, and multi-image composition workflows, while preserving composition and subject layout during edits. The model can return results as image URLs or Base64 data for flexible integration.

Agnes 2.5 Flash is a fully available language model from Sapiens AI, upgraded from Agnes 2.0 Flash and compatible with existing Agnes API integrations. It improves coding, agentic workflows, tool use, multi-turn conversations, reasoning, and image understanding while supporting streaming output and image URL inputs.

Agnes 2.5 Pro is the commercial stable release of Agnes 2.5 Pro Alpha, built for advanced coding, scientific reasoning, long-context analysis, agentic workflows, and multimodal understanding. It supports text and image inputs, text outputs, tool calling, streaming, and OpenAI-compatible Chat Completions and Responses APIs.