- input
- $0.80
- output
- $0.00
- Context
- 128tokens
- Listed
- 2w ago
Cost/1M tokens
Titan Multimodal Embeddings G1 is an Amazon model in the Titan family of foundation models. It converts text, images, or a combination of the two into numerical embeddings in a shared semantic space. It is built for search, recommendation, and personalization use cases, such as finding images by text or by image similarity, and can be fine-tuned on image-text pairs.
How it compares
Frequently asked questions
API and pricing
Titan Multimodal Embeddings G1 costs $0.80 per 1M input tokens and $0.00 per 1M output tokens.
A typical request with 10,000 input tokens and 1,000 output tokens costs $0.008 at the cheapest provider, Amazon Bedrock.
1 tracked endpoint had uptime data in the last day and it was at 99% uptime or better. Best uptime was 100.0%, by Amazon Bedrock.
Privacy and data
Amazon Bedrock offers zero data retention for Titan Multimodal Embeddings G1 (ZDR eligible or 0-day retention).
Capabilities and specs
The context window is 128 tokens and the maximum output is 115 tokens.
Titan Multimodal Embeddings G1 accepts text and image inputs. It does not accept audio, video or PDFs.
Licensing and access
Titan Multimodal Embeddings G1 is available on Amazon Bedrock. There is no tracked endpoint on Azure or Google Vertex AI.
Basics
Titan Multimodal Embeddings G1 was made by Amazon and was first listed on OpenRouter on October 26, 2026.
No. The listed API price is $0.80 input and $0.00 output per 1M tokens, and its openness is unknown.
Generated from Vertical Tabs data, updated November 1, 2026.
Discussion
No comments yet
Be the first to share your thoughts.