amazon
Amazon: Titan Text Embeddings V2
amazon/titan-embed-text-v2
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to its OpenRouter catalog listing, Amazon: Titan Text Embeddings V2 (amazon/titan-embed-text-v2) is a text-to-embeddings model intended for retrieval, search, and clustering. The catalog reports inputs of up to 8,192 tokens and normalized output vectors of 1,024 dimensions. No independent model card or measured benchmark results were included in this source pack, so these capabilities are catalog claims rather than verified performance; validate quality on your own data before adoption.[1]
Strengths
- The OpenRouter catalog reports an 8,192-token input limit, which may suit embedding long passages without aggressive chunking.[1]
- Per the catalog description, it returns normalized 1,024-dimension vectors, a convenient format for similarity computation.[1]
- The listing frames it as purpose-built for embeddings: text input in, embedding output out, with no generative modality.[1]
Limitations
- Evidence is catalog-only: no independent model card, benchmark scores, or usage reports were in this source pack, so all capability claims are unverified and need workload-level validation.[1]
- The catalog lists text as the sole input modality; there is no evidence of image, code, or other multimodal embedding support in this source.[1]
- No supported request parameters are listed, so configurability such as adjustable dimensions or encoding options is undocumented here.[1]
Where to use it
- Plausibly suited to semantic search and retrieval over long documents given the reported token limit; verify embedding quality on your corpus first.[1]
- A candidate for clustering, deduplication, or classification pipelines that consume normalized vectors, subject to empirical testing.[1]
- Could serve as the embedding step in a retrieval-augmented-generation index, pending confirmation that relevance meets your bar.[1]
Sources
- [1] OpenRouter catalog · Amazon: Titan Text Embeddings V2Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering. It accepts up to 8,192 tokens per input and returns normalized vectors of 1,024 dimensions...
Specifications
- Model ID
- amazon/titan-embed-text-v2
- Canonical ID
- amazon/titan-embed-text-v2-20261026
- Creator
- amazon
- Added to OpenRouter
- 26.10.2026
- Context length
- 8,192
- Modality
- text->embeddings
- Input modalities
- text
- Output modalities
- embeddings
- Token pricing
- USD per 1M tokens: in $0.020 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | output: embeddings |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Amazon Bedrock | 8,192 | $0.020 | $0 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.