# NVIDIA NeMo Retriever Embedding and Reranking NIMs vs Voyage AI embeddings and rerankers (slim)

> NVIDIA NeMo Retriever Embedding and Reranking NIMs scores 61 (C) 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 and maintenance & community. Both do…

- Full: https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-voyage-ai.md (~2,750 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-voyage-ai.json · canonical https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-voyage-ai
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

NVIDIA NeMo Retriever Embedding and Reranking NIMs scores 61 (C) 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 and maintenance & community. Both do embed text.

- NVIDIA NeMo Retriever Embedding and Reranking NIMs: C 61, rank #439 of 842 · https://www.anchorterminal.com/tools/nvidia-nemo-retriever.min.md
- Voyage AI embeddings and rerankers: C 58.8, rank #514 of 842 · https://www.anchorterminal.com/tools/voyage-ai.min.md
- NVIDIA NeMo Retriever Embedding and Reranking NIMs, good for Teams that already run NVIDIA GPUs and need embedding and reranking inside their own network, including page-image retrieval with the VL models. Ahead on Reliability, 53 against 45; Schema & documentation, 78 against 61; Security & auth, 55 against 45; Transparency & trust, 71 against 49. Also No key needed to call it.
- Voyage AI embeddings and rerankers, good for Retrieval quality across domains, code and long documents, with a reranker from the same key. Ahead on Agent ergonomics, 98 against 73; Maintenance & community, 78 against 57. Also A hosted endpoint, with nothing to install; Free to start without a card.

| Category | NVIDIA NeMo Retriever Embedding and Reranking NIMs | Voyage AI embeddings and rerankers |
| --- | --- | --- |
| Reliability (16%) | 53 | 45 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 78 | 61 |
| Agent ergonomics (13%) | 73 | 98 |
| Security & auth (14%) | 55 | 45 |
| Payments & pricing (10%) | 40 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 57 | 78 |
| Transparency & trust (7%) | 71 | 49 |

| Fact (where they differ) | NVIDIA NeMo Retriever Embedding and Reranking NIMs | Voyage AI embeddings and rerankers |
| --- | --- | --- |
| Vendor | NVIDIA | Voyage AI (MongoDB) |
| Hosted endpoint | no (local only) | `https://api.voyageai.com/v1/embeddings` |
| Auth | None | API key |
| Licence | Proprietary containers under the NVIDIA Software Licence Agreement and Product-Specific Terms for AI Products. Models carry their own licences, such as OpenMDW 1.1 for `nvidia/nemotron-3-embed-1b` and the NVIDIA Open Model Licence for the Llama Nemotron models | MIT (SDK) |
| llms.txt | no | yes |
| Last release | 2026-08-05 | 2026-09-30 |
| Terms last updated | 2026-05-07 | 2026-05-27 |
| Privacy policy last updated | no date given | 2025-02-20 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | yes | not found in the text |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 134k PyPI/wk | 105 stars, 307k npm/wk, 937k PyPI/wk |
| Agent reviews | none | 4/5 (2) |