Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

Voyage AI review

#52 of 63 in AI Model APIs

A cloud API suite for multilingual, multimodal embeddings and document reranking.

4.3/10Editor score
Visit Voyage AI
Voyage AI4.3 Visit Voyage AI

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

Voyage AI provides hosted cloud APIs for turning unstructured data into vectors and ranking query-document relevance. It targets mid-market and enterprise teams building semantic search, retrieval-augmented generation, and related AI applications. The service covers text embeddings, multilingual models, multimodal embeddings for interleaved text, images, and videos, contextualized chunk embeddings, code-oriented models, and reranking. REST endpoints plus official Python and TypeScript libraries support application integration.

Pricing is usage-based, with no free plan. voyage-4-lite costs $0.02 per 1 million tokens for a general-purpose model optimized for latency and cost. voyage-4 is $0.06 per 1 million tokens for general-purpose and multilingual embeddings, while voyage-4-large is $0.12 per 1 million tokens for the highest-quality general-purpose and multilingual embeddings. voyage-multimodal-3.5 costs $0.12 per 1 million text tokens for interleaved text, image, and video embeddings. rerank-3-lite is $0.02 per 1 million tokens, and rerank-3 is $0.05 per 1 million tokens. Published token rates apply after account free-token allowances; multimodal image usage is separately priced by pixels. Batch processing offers discounted bulk processing, and the Files API stores batch inputs and outputs.

Its ecosystem includes DataStax Astra DB, Haystack, LanceDB, LangChain, LlamaIndex, MyScale, Redis, Unstructured, Weaviate, Zilliz, Milvus, Pinecone, and Qdrant. That breadth suits teams connecting retrieval models to established vector databases and orchestration frameworks. Email, community, and documentation channels provide support. Choose Voyage AI when embedding quality, multimodal retrieval, reranking, and vector-database compatibility are priorities. Teams seeking a free tier, self-hosted deployment, or a broader language-model generation platform should consider alternatives.

Voyage AI pros and cons

  • Where it wins
    • Text, image, and video embeddings support multimodal retrieval
    • Reranking, contextualized chunks, batch processing, and files APIs
    • Integrates with major vector databases and AI frameworks
  • Where it doesn't
    • No free plan; usage is billed by token
    • Cloud deployment only, with no self-hosted option listed
    • Focused on retrieval APIs rather than language-model generation

Voyage AI fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update