# Reka

> Reka's multimodal model family (Flash, Edge) for text, image, and video

- Category: [Multimodal & Perception](https://ailandscape.org/category/multimodal-perception) › Vision-Language Models
- Homepage: https://reka.ai
- Tags: multimodal, vision, api, open-weights
- Also known as: Reka Core, Reka Flash, Reka Edge
- Added to the landscape: 2026-03-18

## Similar tools in Vision-Language Models

- [Flamingo](https://ailandscape.org/tool/flamingo): DeepMind's 2022 few-shot visual language model; weights not released
- [InternVL](https://ailandscape.org/tool/internvl): Shanghai AI Lab's open multimodal model family, up to 241B MoE
- [LLaVA](https://ailandscape.org/tool/llava): Open visual instruction tuning VLM family, incl. LLaVA-NeXT and OneVision
- [moondream](https://ailandscape.org/tool/moondream): Open vision-language models by M87 Labs, with fine-tuning and a cloud API
- [Qwen-VL](https://ailandscape.org/tool/qwen-vl): Alibaba's visual language model with strong document understanding

---

Part of [AI Landscape](https://ailandscape.org), an open map of the AI ecosystem. Web page: https://ailandscape.org/tool/reka · Index for AI assistants: https://ailandscape.org/llms.txt