Back to Models

Amazon Titan Text Embeddings V2

amazonamazon/titan-embed-v2

How TheRouter serves this differently from the vendor

As the vendor operates it

AWS serves Titan Text Embeddings V2 on the Bedrock bedrock-runtime endpoint with Invoke, text input, embedding output, an 8K-token / 50,000-character input ceiling, model id amazon.titan-embed-text-v2:0, and no cross-region inference profile on the current model card.

On TheRouter

TheRouter serves the same embedding model as amazon/titan-embed-v2 through /v1/embeddings with OpenAI-compatible client syntax. Operational price, context, modality, and supported-parameter fields come from the live TheRouter catalog; the curated page documents AWS source-of-truth behavior and leaves snippets capped until an operator-funded verification run records execution.

API guide

Embeddings request

Generate embeddings for a text input with configurable dimensions and optional normalization. TheRouter routes your request transparently to Amazon Bedrock with fully OpenAI‑compatible syntax.

cURL
curl https://api.therouter.ai/v1/embeddings \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "amazon/titan-embed-v2",
    "input": "Your text to embed here.",
    "dimensions": 256,
    "encoding_format": "float"
  }'

Dimension and normalization policy

Pick 256, 512, or 1024 dimensions per index and keep the choice stable. Normalization should also be set deliberately because it changes vector distance behavior in the downstream database.

cURL
curl https://api.therouter.ai/v1/embeddings \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "amazon/titan-embed-v2",
    "input": ["First passage", "Second passage"],
    "dimensions": 512,
    "normalize": true
  }'
Fact ledger — every claim on this page traces here
sourceURLretrieved
Release dateAmazon Bedrock docs ↗2026-08-23verified
Output dimensionsdocs.aws.amazon.com ↗2026-08-23verified
Vector normalizationdocs.aws.amazon.com ↗2026-08-23verified
Supported languagesdocs.aws.amazon.com ↗2026-08-23verified
Max input charactersdocs.aws.amazon.com ↗2026-08-23verified
Training cutoff——unknown
Tokens‑to‑characters ratio (English)docs.aws.amazon.com ↗2026-08-23verified
MTEB (Massive Text Embedding Benchmark) weighted averageAWS ML blog ↗2026-08-23verified
MTEB rerankingaws.amazon.com ↗2026-08-23verified
MIRACL multilingualaws.amazon.com ↗2026-08-23verified
Amazon Titan Text Embeddings V2 now available in Amazon BedrockAWS News Blog ↗2026-08-23verified
Get started with Amazon Titan Text Embeddings V2: A new state‑of‑the‑art embeddings model on Amazon BedrockAWS Machine Learning Blog ↗2026-08-23verified
What are the practical accuracy‑storage trade‑offs between 256, 512, and 1024 dimensions?aws.amazon.com ↗2026-08-23to verify
Does Titan V2 support cross‑language search (e.g., query in German against a corpus in Korean)?docs.aws.amazon.com ↗2026-08-23to verify
Why does Bedrock throttle embedding models by RPM instead of TPM? What’s the performance implication?docs.aws.amazon.com ↗2026-08-23to verify
What’s the difference between Titan V2 and its predecessor Titan G1 (V1)?aws.amazon.com ↗2026-08-23to verify
Help & contact