TechPrufer
Get started
Together AI
Together AI logoTogether AI · Feature trail

Video Generation Models

6 posts · Oct 2025 – Jul 2026

What this trail covers

Together AI now offers native deployment of elite proprietary image and video generation models, including FLUX.2 from Black Forest Labs, OpenAI's Sora 2 Pro, Google's Veo 3.0 and Imagen 4.0 Ultra, ByteDance's Seedream 1.0 Pro, and the Wan 2.7 suite. This expansion includes over 40 new models, enabling complete workflows that combine text, image, and video generation within a single application. The platform provides OpenAI-compatible endpoints, unified authentication, and transparent per-model usage. FLUX.2 specifically targets production-grade image generation with multi-reference input for character/product consistency, hex code color matching for brand compliance, and improved text rendering. It is available in Dev, Pro, and Flex variants, served through Together AI's fast, reliable infrastructure with the same APIs used across the rest of the generative stack.

All Together AI trails
  1. Together AI brings Thinking Machines Lab’s new model Inkling on day 0This 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.
  2. Wan 2.7 video model suite now available on Together AIThis post announces the availability of the Wan 2.7 video model suite on Together AI, specifically highlighting the text-to-video model (`Wan-AI/wan2.7-t2v`) which is available now. It details the model's capabilities including flexible resolution (720P and 1080P), duration control (2 to 15 seconds), optional audio input, and prompt-driven narrative control. The post also previews upcoming image-to-video, reference-to-video, and video edit models, outlining their respective features. It emphasizes the integration of these video models into the existing Together AI platform, providing a unified API, authentication, and billing surface. A Python code example for using the text-to-video model is provided.
  3. FLUX.2: Multi-reference image generation now available on Together AIThis post introduces FLUX.2, a new image generation model from Black Forest Labs, to the Together AI platform. It highlights FLUX.2's production-grade capabilities, specifically multi-reference input for character and product consistency, hex code color matching for brand compliance, and improved text rendering. The post details the technical specifications of FLUX.2 (Dev, Pro, Flex variants) including resolution, generation time, and context length. It emphasizes seamless integration with Together AI's existing infrastructure, using the same SDK, authentication, and billing as LLM and voice workloads. Code examples demonstrate using the Python SDK for image generation.
  4. Expanding Together AI Model Library into multimedia generation with 40+ new image and video modelsThis post announces the expansion of Together AI's model library to include over 40 new image and video generation models, integrating with partners like Runware.ai. It highlights the addition of models such as OpenAI Sora 2 Pro, Google Veo 3.0, and ByteDance Seedream 1.0 Pro for video generation, and Google Imagen 4.0 Ultra and Gemini Flash Image 2.5 (Nano Banana) for image generation. The post emphasizes the ability to build complete generative media workflows within a single platform, combining text, image, and video generation through OpenAI-compatible APIs. It details production deployment options including serverless auto-scaling and enterprise reliability, and provides a Python code example for creating a video generation job.