Model comparison
Nova 2 Lite vs Titan Text Embeddings V2
Compare Nova 2 Lite and Titan Text Embeddings V2: input/output $/Mtoken, context window, modalities, and license. OpenRouter-synced pricing.
Amazon
Nova 2 Lite
Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilit
Amazon
Titan Text Embeddings V2
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
| Metric | Nova 2 Lite | Titan Text Embeddings V2 |
|---|---|---|
| Provider | Amazon | Amazon |
| Context window | 1,000,000 | 8,192 |
| Input $/Mtok | $0.300 | $0 |
| Output $/Mtok | $2.50 | $0 |
| Modalities | text, vision, video | text |
| License | closed | closed |
Quick take
On input price, Titan Text Embeddings V2 is cheaper at $0/Mtok. For context window, Nova 2 Lite leads with 1,000,000 tokens.
Pick based on your workload: high-volume cheap inference vs long-document / agent loops. Enterprise DNA can wire either model into Omni with evals, secrets, and job orchestration.