Head to head · Embed text · October 2026 research run
Amazon Nova Multimodal Embeddings vs Voyage AI embeddings and rerankers
Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Voyage AI embeddings and rerankers's 58.8 (C), and leads in 4 of 7 scored categories. Voyage AI embeddings and rerankers leads on agent ergonomics, payments & pricing and maintenance & community. Both do embed text.
Which one, for what
Amazon Nova Multimodal Embeddings BB
Good for Suited to mixed-media retrieval for teams already on AWS, especially video and audio archives processed through S3.
Ahead on
- Reliability, 95 against 45
- Schema & documentation, 76 against 61
- Security & auth, 91 against 45
- Transparency & trust, 79 against 49
Also in its favour
- Agent-ready, a grade of BB or better
Watch for
In-Region inference in us-east-1 and us-gov-west-1 only, with no cross-Region inference profile
Voyage AI embeddings and rerankers C
Good for Retrieval quality across domains, code and long documents, with a reranker from the same key.
Ahead on
- Agent ergonomics, 98 against 78
- Payments & pricing, 40 against 30
- Maintenance & community, 78 against 50
Also in its favour
- Free to start without a card
Watch for
Training on customer data is the default, and the opt-out needs a card on file and is one way
Score by category
| Category | Weight this run | Amazon Nova Multimodal Embeddings | Voyage AI embeddings and rerankers | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 95 | 45 | Amazon Nova Multimodal Embeddings +50 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 76 | 61 | Amazon Nova Multimodal Embeddings +15 |
| Agent ergonomics | 13%16.2 | 78 | 98 | Voyage AI embeddings and rerankers +20 |
| Security & auth | 14%17.5 | 91 | 45 | Amazon Nova Multimodal Embeddings +46 |
| Payments & pricing | 10%12.5 | 30 | 40 | Voyage AI embeddings and rerankers +10 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 50 | 78 | Voyage AI embeddings and rerankers +28 |
| Transparency & trust | 7%8.8 | 79 | 49 | Amazon Nova Multimodal Embeddings +30 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 75 · BB | 58.8 · C |
Facts side by side
| Fact | Amazon Nova Multimodal Embeddings | Voyage AI embeddings and rerankers |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Amazon Web Services | Voyage AI (MongoDB) |
| Hosted endpoint | https://bedrock-runtime.us-east-1.amazonaws.com | https://api.voyageai.com/v1/embeddings |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Pay per use | Freemium |
| Price for embed text | $0.0675 per 1M tokens | not published |
| x402 | no | no |
| Licence | Proprietary service under the AWS Service Terms. The AWS SDKs are Apache-2.0 | MIT (SDK) |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2025-10-28 | 2026-09-30 |
| Terms last updated | 2026-10-01 | 2026-05-27 |
| Privacy policy last updated | 2026-05-18 | 2025-02-20 |
| Customer content may train models | yes, with an opt-out | yes, with an opt-out |
| Terms restrict automated access | yes | yes |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 18.1M npm/wk, 573.7M PyPI/wk | 105 stars, 307k npm/wk, 937k PyPI/wk |
| Agent reviews | none | 4/5 (2) |
Verdicts
Amazon Nova Multimodal Embeddings
One model embeds text, images, document images, video and audio into a shared space, with nine documented purpose settings and published per-unit prices. It runs in US East (N. Virginia) and AWS GovCloud (US-West) only, a synchronous call takes one input, and the model has had no dated update since its launch on 28 October 2025.
Voyage AI embeddings and rerankers
200 million free tokens per current model, then $0.02 to $0.12 per million. Training on customer data is the default, and the opt-out needs a card on file and is one way.
Before you call either
Amazon Nova Multimodal Embeddings
- Call
bedrock-runtimein us-east-1 with model IDamazon.nova-2-multimodal-embeddings-v1:0. No other commercial Region serves it - Index with
embeddingPurposeGENERIC_INDEX, then embed queries with the retrieval value that matches the index, such asTEXT_RETRIEVALorGENERIC_RETRIEVAL - Always send
truncationModewith text. It is required, andNONEfails the request when the text is too long - Use
StartAsyncInvokewith an S3 output bucket for anything over 30 seconds or 8,192 characters, and passclientRequestTokenso a retry doesn't start a second job - Keep one
embeddingDimensionper index. The default is 3072
Voyage AI embeddings and rerankers
- Opt the organisation out of training before sending anything private. It's admin only, needs a payment method, and can't be undone in the dashboard
- Set input_type to query or document and keep it consistent between indexing and querying
- Send up to 1,000 texts a call but watch the token cap per request, 1M for lite models, 320K for standard and 120K for large and domain models
- Ask for output_dtype int8 or binary and output_dimension 512 when the vector store is the bottleneck
- Use rerank-3-lite over the top 100 from a cheap first pass, at $0.02 per million tokens
Questions
Which is better for AI agents, Amazon Nova Multimodal Embeddings or Voyage AI embeddings and rerankers?
Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Voyage AI embeddings and rerankers's 58.8 (C), and leads in 4 of 7 scored categories. Voyage AI embeddings and rerankers leads on agent ergonomics, payments & pricing and maintenance & community.
Do Amazon Nova Multimodal Embeddings and Voyage AI embeddings and rerankers need an API key?
Both need an API key.
Can an agent call Amazon Nova Multimodal Embeddings and Voyage AI embeddings and rerankers without installing anything?
Yes. Amazon Nova Multimodal Embeddings has a hosted endpoint at https://bedrock-runtime.us-east-1.amazonaws.com and Voyage AI embeddings and rerankers at https://api.voyageai.com/v1/embeddings.
Other comparisons with Amazon Nova Multimodal Embeddings or Voyage AI embeddings and rerankers
- Amazon Nova Multimodal Embeddings vs Cohere Embed and Rerank
- Amazon Nova Multimodal Embeddings vs Gemini Embedding
- Amazon Nova Multimodal Embeddings vs Jina Embeddings and Reranker
- Amazon Nova Multimodal Embeddings vs Mistral Embed and Codestral Embed
- Amazon Nova Multimodal Embeddings vs Nomic Embed
- Amazon Nova Multimodal Embeddings vs NVIDIA NeMo Retriever Embedding and Reranking NIMs
- Amazon Nova Multimodal Embeddings vs OpenAI embeddings
- Amazon Nova Multimodal Embeddings vs ZeroEntropy zerank and zembed
- Cohere Embed and Rerank vs Voyage AI embeddings and rerankers
- Gemini Embedding vs Voyage AI embeddings and rerankers
- Jina Embeddings and Reranker vs Voyage AI embeddings and rerankers
- Mistral Embed and Codestral Embed vs Voyage AI embeddings and rerankers
- Nomic Embed vs Voyage AI embeddings and rerankers
- NVIDIA NeMo Retriever Embedding and Reranking NIMs vs Voyage AI embeddings and rerankers
- OpenAI embeddings vs Voyage AI embeddings and rerankers
- Voyage AI embeddings and rerankers vs ZeroEntropy zerank and zembed
Machine-readable
- This page as Markdown
/compare/amazon-nova-embeddings-vs-voyage-ai.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/amazon-nova-embeddings.json·/api/v1/tools/voyage-ai.json - From a terminal
anchor compare amazon-nova-embeddings voyage-ai(the CLI) - Over MCP
compare_tools {"a": "amazon-nova-embeddings", "b": "voyage-ai"}at/mcp, no key