One API for 600+ image, video, audio and text models, with fallback routing, versioned workflows and pay-per-call pricing.
Paid
Voyage AI
Embedding models and rerankers, billed by usage, for search and retrieval-augmented generation pipelines.
What is Voyage AI?
Voyage AI provides text and multimodal embedding models plus rerankers that developers use to improve semantic search and retrieval-augmented generation. The embedding endpoint turns documents and queries into vectors, with general-purpose and multilingual models (the voyage-4 series), a code-focused model, and finance and legal models, mostly with 32,000-token context and a choice of 256, 512, 1024 or 2048 dimensions. The multimodal endpoint accepts text, images and video frames, and the reranker reorders retrieved documents before they reach the language model. Everything is reached through an API and a Python package named voyageai, and an open-weight voyage-4-nano model is published on Hugging Face. A Batch API gives a 33% discount with a 12-hour completion window. Pricing is usage-based: every account gets free tokens, such as 200 million for voyage-4, and after that voyage-4-lite costs $0.02 per million tokens while voyage-4-large costs $0.12 per million.
Use cases
- Embed documents for semantic search
- Rerank retrieved results for RAG
- Retrieve code for coding agents
- Search finance and legal documents
- Embed images and video frames
- Run batch embedding jobs at a discount
- Fine-tune embeddings with dedicated support
Who it's for
Why use Voyage AI
- Pay-per-token billing with a large free allowance lets you prototype retrieval without a commitment.
- Embeddings and rerankers come from one vendor, so a retrieval pipeline needs fewer separate services.
- Domain models for code, finance and law target specialized document sets.
- Smaller output dimensions can lower vector storage and search costs.
- Batch processing cuts the price of large offline embedding jobs.
Voyage AI features
- General-purpose and multilingual embeddings in the voyage-4 series
- Code embeddings with voyage-code-4
- Finance and legal embedding models
- Multimodal embeddings for text, images and video frames
- Rerankers such as rerank-2.5 and rerank-2.5-lite
- Adjustable output dimensions of 256, 512, 1024 or 2048
- 32,000-token context on most current text models
- Batch API with a 33% discount
- Files API with 30-day retention
- Open-weight voyage-4-nano on Hugging Face
- Python package voyageai
Voyage AI integrations
How to get started with Voyage AI
- Create an account and an API key in the Voyage dashboard, and add a payment method to reach usage tier 1.
- Install the voyageai Python package, or call the REST API directly.
- Send documents and queries to the embedding endpoint with a chosen model and input type, then store the vectors in your vector database.
- Retrieve candidates by similarity, then pass them to the reranker endpoint to reorder the results.
- Send the top results to your language model, and watch usage and rate limits in the dashboard.
Voyage AI limitations
- Free tokens do not apply to Batch API usage
- Rate limits start at 2000 requests per minute and rise with usage tiers
- Older models receive no free tokens
- Fine-tuned models with dedicated instances require contacting sales
Voyage AI pricing
Yes, Voyage AI has a free plan. Paid plans start at $0.02 usage-based, according to the official pricing page on .
Voyage AI plans
voyage-4-lite
$0.02 per million tokens
Usage-based
- 200 million free tokens
- 32,000-token context
voyage-4
$0.06 per million tokens
Usage-based
- 200 million free tokens
- 32,000-token context
voyage-4-large
$0.12 per million tokens
Usage-based
- 200 million free tokens
- 32,000-token context
voyage-code-4
$0.12 per million tokens
Usage-based
- 200 million free tokens
- Optimized for code retrieval
voyage-multimodal-3.5
$0.12 per million tokens
Plus $0.60 per billion pixels
- 200M text tokens free
- 150B pixels free
rerank-3-lite
$0.02 per million tokens
Usage-based
- 200 million free tokens
Plans as listed on the official pricing page on . Prices can change and may vary by country or exclude tax. Check the official pricing page.
Voyage AI alternatives
The main Voyage AI alternatives listed on Debuly are Jina AI, Cohere, Together AI, OpenAI API, Chroma and Cognee. The table compares pricing and platforms; order is A–Z.
| Tool | Pricing | Starting price | Platforms |
|---|---|---|---|
| Voyage AI | Freemium | $0.02, usage-based | API, Python |
| Chroma | Open source | $250/mo | API, CLI, Self-hosted, Web |
| Cognee | Freemium | $1, usage-based | Web, API, Self-hosted, MCP server |
| Cohere | Freemium | — | API, Web, Private deployment |
| Jina AI | Freemium | — | API, AWS SageMaker, Microsoft Azure, Google Cloud |
| OpenAI API | Paid | $0.1, usage-based | API, Web |
| Together AI | Paid | — | Web, API |
Chroma
Open-source search database for AI apps, with vector, full-text, regex and metadata search and a serverless cloud option.
Open sourceVisit Chroma (official site)
Cognee
Open-source memory engine for AI agents that combines vector search, knowledge graphs and relational storage, with a hosted cloud.
FreemiumVisit Cognee (official site)
Cohere
Enterprise AI company offering Command, Embed and Rerank models by API, the North agent platform and private deployments.
FreemiumVisit Cohere (official site)
Jina AI
Search foundation model APIs: multilingual and multimodal embeddings, rerankers, document OCR and a Reader that turns URLs into Markdown.
FreemiumVisit Jina AI (official site)
OpenAI API
Developer API for OpenAI's GPT models, image generation, realtime voice and transcription, priced per million tokens with batch and flex options.
Together AI
AI cloud for running open-source models through serverless and batch inference, dedicated endpoints, GPU clusters and fine-tuning.
Voyage AI FAQ
How much does Voyage AI cost?
Pricing is usage-based. Examples per million tokens: voyage-4-lite $0.02, voyage-4 $0.06, voyage-4-large $0.12, and voyage-multimodal-3.5 $0.12 plus $0.60 per billion pixels.
Is there a free plan for Voyage AI?
There is no plan tier, but every account gets free tokens. The first 200 million tokens for voyage-4 series models and voyage-code-4 are free.
What does Voyage AI charge for rerankers?
The reranker is billed per processed token. On the pricing page, rerank-3 is $0.05 per million tokens and rerank-3-lite is $0.02 per million, with 200 million free tokens.
Does Voyage AI have an API?
Yes. Voyage is API-first, with a Python package named voyageai and a rate-limited REST API that includes a Batch API and a Files API.
Is there a cheaper way to run large jobs?
The Batch API completes requests within 12 hours at a 33% discount compared with standard endpoints, though free token credits do not apply to it.
Is Voyage AI open source?
The main service is hosted, but the voyage-4-nano embedding model is published as an open-weight model on Hugging Face.
What are alternatives to Voyage AI?
Alternatives for embeddings and reranking include OpenAI embeddings, Cohere Embed and Rerank, Jina AI, Google Gemini embeddings and Nomic Embed.
Sources & verification
Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.
| Source | Type | Accessed |
|---|---|---|
| voyageai.com/ | official | |
| docs.voyageai.com/docs/pricing | pricing | |
| docs.voyageai.com/docs/rate-limits | docs | |
| docs.voyageai.com/docs/embeddings | docs |
Image credits
- Logo: from voyageai.com · fetched · Vendor trademark, used only to identify the product; removed on request
- Cover: none collected yet, so a generated tile is shown.
Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.
More in Developer platforms 4
All developer platforms toolsGoogle's developer API for calling Gemini models from your own apps, with a free tier, pay-as-you-go pricing and Google AI Studio.
FreemiumFree browser calculators and an error debugger for PyTorch tensor shapes, plus a $29 one-time local toolkit called Tensor Preflight.
FreemiumVS Code extension and team dashboard that measure how much code your AI coding tools write, how much survives to commit, and which models earn their cost.
Free
