Amazon: Titan Multimodal Embeddings G1
- by amazon
- amazon/titan-embed-image-v1
Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. Images are sent as base64 (up to...
What the numbers mean
- Context window128 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 96 words, or 0 pages.
- Max output115 tokens
- The longest single reply it can write: about 86 words.
- Input price$0.8 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output priceFree
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs nothing.
- Modalitiestext, image in, embeddings out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.