# Amazon Bedrock Titan Embeddings vs Google Vertex AI Text Embeddings

| Attribute | Amazon Bedrock Titan Embeddings | Google Vertex AI Text Embeddings |
|---|---|---|
| **Vioscale score** | 57.5 (21% (low)) | 43.9 (36% (low)) |
| deployment.options | `{"cloud":true}` | `{"cloud":true}` |
| description.long | - | A cloud-based API that transforms text into high-dimensional vector embeddings using deep learning. Supports multiple languages and task types, integrating with vector databases for efficient semantic search. |
| features.capabilities | - | `{"pricing_model":"per_million_tokens_api","architecture_model":"managed_cloud_api","multi_modal_image_and_text_joint_embeddings":true,"massive_context_window_greater_than_8k_tokens":true,"multilingual_support_across_100_plus_languages":true,"task_specific_prefixes_query_vs_document_instructions":true}` |
| integrations.count | - | 1 |
| integrations.list | - | `[{"name":"Vector Search"}]` |
| market.availability | `{"hqCountry":"US","primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | `{"primaryMarkets":["US"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"cli":true,"web":true}` | `{"cli":true,"web":true}` |
| pricing | - | `{"type":"usage","summary":"Free credits ($300) for new customers; usage-based pricing thereafter","currency":"USD","freeTier":true,"sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings","retrievedAt":"2026-08-21T11:04:41.911Z"}` |
| pricing.free_tier | yes | yes |
| pricing.model | freemium | freemium |
| pricing.price_level | - | low |
| pricing.transparent | - | no |
| security.fedramp | yes | - |
| security.gdpr | yes | - |
| security.hipaa | yes | - |
| security.iso27001 | yes | - |
| security.pci | yes | - |
| security.soc2 | yes | - |

## Capabilities (Embeddings Apis)

| Capability | Amazon Bedrock Titan Embeddings | Google Vertex AI Text Embeddings |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Architecture model | - | Managed cloud API |
| Matryoshka representation learning for dimension truncation | - | - |
| Multilingual support across 100 plus languages | - | ✓ |
| Binary and scalar quantization for memory reduction | - | - |
| Cross encoder reranker API offered | - | - |
| Late interaction architecture colbert v2 | - | - |
| Massive context window greater than 8k tokens | - | ✓ |
| Multi modal image and text joint embeddings | - | ✓ |
| Task specific prefixes query vs document instructions | - | ✓ |
| Zero data retention training opt out enterprise | - | - |
| SOC2 type ii | - | - |
| Mit or apache permissive oss license | - | - |
| Pricing model | - | Per million tokens API |

*Source: Vioscale. Generated 2026-09-01T17:29:08.937Z. "-" = undocumented, not absent.*