gme-qwen2-vl-2b-instruct

by Qwen

The GME-Qwen2VL series is a unified multimodal Embedding model trained based on the Qwen2-VL multimodal large language model (MLLMs). The GME model supports three types of inputs: text, images, and image-text pairs. All these input types can generate universal vector representations and exhibit excellent retrieval performance.

API Pricing

Input	$0.14 / 1M tokens
Output	$0.14 / 1M tokens

Specifications

Modalities

text, image, video

Use gme-qwen2-vl-2b-instruct via the AIHubMix unified API — one interface for every major LLM.