TechPrufer
Sign inGet started

Blogs›Together AI›Video Generation Models

Video Generation Models

Video Generation Models

4
posts
2025–2026

Together AI now offers native deployment of elite proprietary image and video generation models, including OpenAI's Sora 2 Pro, Google's Veo 3.0 and Imagen 4.0 Ultra, and ByteDance's Seedream 1.0 Pro. This enables high-quality, production-grade media generation with advanced features like multi-shot storytelling, cinematic quality, and advanced camera control. The platform provides unified tooling, SDKs, authentication, and billing for multimodal workloads, allowing for tighter creative control. Additionally, Together AI now offers native deployment of Thinking Machines Lab's Inkling model, a multimodal mixture-of-experts model supporting text, image, and audio inputs with controllable inference effort and a 1M context window. Inkling features query-conditioned relative attention, short causal convolutions, and a shared-sink MoE architecture, optimized for efficient production inference on Together AI's platform using a FlashAttention-4-based kernel.

2026

Together AI brings Thinking Machines Lab’s new model Inkling on day 0

7/15/2026

This post announces the availability of the Inkling multimodal model on Together AI's inference platform. It details Inkling's architecture, including query-conditioned relative attention, short causal convolutions, and a shared-sink MoE, and highlights its multimodal input capabilities (text, image, audio) and controllable reasoning effort. The post also emphasizes the optimization of Inkling for production inference on Together AI, specifically mentioning the use of a FlashAttention-4-based kernel to support its attention mechanism.

Wan 2.7 video model suite now available on Together AI

4/3/2026

This post introduces the availability of the Wan 2.7 video model suite on Together AI, specifically detailing the text-to-video model (`Wan-AI/wan2.7-t2v`) which is available now. It highlights features such as flexible resolution (720P and 1080P), duration control (2-15 seconds), optional audio input, and prompt-driven narrative control. The post also announces upcoming availability for image-to-video, reference-to-video, and video edit models, outlining their respective capabilities. It emphasizes the integration into the existing Together AI platform with consistent APIs, authentication, and billing, and provides a Python code example for using the text-to-video endpoint.

2025

FLUX.2: Multi-reference image generation now available on Together AI

11/25/2025

Introduces FLUX.2, a new image generation model with multi-reference input for character/product consistency, hex code color matching, and improved text rendering. Details technical specifications like resolution, generation time, and context length for different FLUX.2 variants (dev, pro, flex). Highlights platform integration with existing SDKs, serverless, and dedicated deployments, emphasizing unified auth, billing, and monitoring. Provides a Python SDK code example for image generation.

Expanding Together AI Model Library into multimedia generation with 40+ new image and video models

10/21/2025

This post announces the expansion of Together AI's model library to include over 40 new image and video generation models, significantly enhancing its generative media capabilities. It introduces new video generation APIs with models like OpenAI Sora 2 Pro, Google Veo 3.0, and Minimax Hailuo, capable of creating 4-30 second videos at various resolutions and styles. It also adds over 15 new image models, including Google Imagen 4.0 Ultra and Nano Banana, for versatile image creation and editing. The post highlights the ability to build complete workflows by combining text, image, and video generation within a single platform, simplifying development for applications in gaming, advertising, and education. Production deployment options include serverless endpoints with enterprise-grade infrastructure, rate limits, auto-scaling, and global availability, all accessible through OpenAI-compatible APIs and a unified billing platform. A Python code example demonstrates how to create and poll for video generation jobs.