Multimodal AI
16 items tagged with "multimodal-ai"
Models16
Gemini Omni 1.2 Flash
Google's fast, cost-effective Gemini Omni model with native 15-second video generation and editing, improved consistency, and lower pricing.
Images 2.6
OpenAI's image generation and editing model update with faster generation, GIF creation, more precise editing, and new API controls across ChatGPT, Codex, and the API.
Gemini Omni 1.1 Flash
Google Gemini Omni Flash model variant listed on OpenRouter with a 131k-token context window for multimodal generation and editing workflows.
Pegasus 1.5
TwelveLabs Pegasus 1.5 is a video language model now available in Amazon Bedrock. It turns long-form video into structured, timestamped metadata and supports video segmentation, multimodal prompting with reference images, and JSON outputs.
Nemotron 3.5 Super VL
NVIDIA open 120-billion-parameter vision-language model for specialized always-on agents. It is described as delivering high task-completion efficiency and accuracy for agentic workloads.
Moondream3 Preview
Preview release of Moondream's third-generation vision-language model family, added to OpenRouter with a 32K-token context window. It is intended for image understanding and multimodal assistants.
Moondream3.1 9B A2B
Moondream 3.1 9B A2B vision-language model added to OpenRouter with a 32K-token context window. It targets efficient multimodal image understanding and visual assistant use cases.
GPT-6
OpenAI's GPT-6 model is rolling out globally in ChatGPT with Intelligent UI, enabling faster responses with visuals and interactive experiences. OpenAI also published a model guide for the GPT-6 family during the tracked date range.
Qwen3-VL-8B
Qwen3-VL-8B is a Qwen3 vision-language model referenced for multimodal reinforcement-learning post-training with GRPO on Amazon SageMaker HyperPod.
Qwen3.8 Omni Flash
Qwen3.8 Omni Flash is an Alibaba Qwen model listed on OpenRouter with a 1M-token context window, positioned as a fast omni-capable model in the Qwen3.8 family.
ChatGPT Images 2.5
OpenAI image-generation and image-editing model for turning ideas, sketches, and reference photos into more personalized, polished images.
DeepSeek V4 Flash Vision Exp
Experimental vision-capable variant of DeepSeek V4 Flash available on OpenRouter, adding multimodal image understanding to the Flash model line with a 1M-token context window.
Amazon Nova 2 Lite
Amazon Nova 2 Lite is a lightweight multimodal Nova model referenced for cost-optimized scanned document processing, where it handles native multimodal extraction before downstream Claude processing.
Gemini 3.1 Flash Image
Google Gemini image-focused model listed on OpenRouter with a 131,072-token context window. It is positioned as a Flash-tier multimodal/image model for lower-latency image-centric workloads.
Gemini 3 Pro Image
Google Gemini Pro-tier image-focused model listed on OpenRouter with a 65,536-token context window. It targets higher-capability multimodal and image-generation use cases than Flash-tier variants.
Gemini Omni
Gemini Omni is a Google Gemini-family model announced at Google I/O 2026 and showcased in Google demos alongside Gemini 3.5. The discovery data verifies the announcement but does not provide context length, output limit, or pricing details.