# Voyage AI embeddings and rerankers (slim)

> Embedding and reranking models for text, code and multimodal retrieval from MongoDB-owned Voyage AI.

- Full: https://www.anchorterminal.com/tools/voyage-ai.md (~6,300 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/voyage-ai.json · canonical https://www.anchorterminal.com/tools/voyage-ai
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**C · 59/100 · rank #273 of 452 · #5 in Embeddings & rerankers · not agent-ready · confidence medium**


Assessment: 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.

## Facts

- Kind: HTTP API · vendor: Voyage AI (MongoDB) · category: Embeddings & rerankers · legal entity: Voyage AI Innovations, Inc. · provenance 76/100
- Endpoint: `https://api.voyageai.com/v1/embeddings` (HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: MIT (SDK)
- Probe metrics: not measured yet (probes haven't run)
- Free tier: 200 million tokens per current model, no card. 50 million for the -2 models
- Dimensions: 256, 512, 1024 (default) or 2048 on the voyage-4 series and voyage-code-4. 1024 fixed on voyage-finance-2 and voyage-law-2
- Max context: 32,000 tokens on the voyage-4 series, voyage-code-4, voyage-finance-2 and the rerank-3 models. 16,000 on voyage-law-2
- Languages: Multilingual on the voyage-4 series. No published language count
- Output types: float, int8, uint8, binary, ubinary
- Request limits: 1,000 texts a call. 1M tokens a request for lite models, 320K standard, 120K large and domain models. Rerank up to 1,000 documents
- Rate limits: Tier 1 (payment method added) 2,000 requests a minute and 2M to 16M tokens a minute by model. 2x at $100 paid, 3x at $1,000
- Trains on API data: Yes by default. Admin opt-out in the dashboard, then inputs are deleted after processing
- Multimodal: voyage-multimodal-3.5 takes interleaved text, images and video at a separate multimodalembeddings endpoint. Images up to 16 million pixels and 20 MB
- MCP server: None official
- Prices: voyage-4-large embeddings $0.12 per 1M tokens; voyage-4 embeddings $0.06 per 1M tokens; voyage-4-lite embeddings $0.02 per 1M tokens; rerank-3 $0.05 per 1M tokens; rerank-3-lite $0.02 per 1M tokens; Files API storage $0.05 per GB per month

- Scores: Reliability 45, Performance pending, Schema & documentation 61, Agent ergonomics 98, Security & auth 45, Payments & pricing 40, Task success pending, Maintenance & community 78, Transparency & trust 51 · total over the 7 assessed categories
- Why: Reliability, status.voyageai.com timed out on 30 September, 1 October and twice on 2 October 2026, and neither the site footer nor the docs index links a… · Schema & documentation, No public OpenAPI file found (0 of 25). · Agent ergonomics, output_dimension 256 to 2048 and float, int8, uint8, binary or ubinary output per request, plus top_k on rerank (25). · Security & auth, Plain API keys from the dashboard, revocable, no scopes (20). · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, rerank-3 and rerank-3-lite went GA on 30 September 2026, two days ago (30). · Transparency & trust, Closed service under published terms, SDK MIT, voyage-4-nano weights on Hugging Face (15).
- Sources: 14, open questions: 4, both in the full twin
- Capabilities: embed.text, embed.multimodal, embed.code, embed.multilingual, rerank
- JSON: https://www.anchorterminal.com/api/v1/tools/voyage-ai.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/voyage-ai.svg` or a link to https://www.anchorterminal.com/tools/voyage-ai from a page on voyageai.com or mongodb.com or one of their subdomains, or the README of github.com/voyage-ai/voyageai-python, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. 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
2. Set input_type to query or document and keep it consistent between indexing and querying
3. 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
4. Ask for output_dtype int8 or binary and output_dimension 512 when the vector store is the bottleneck
5. Use rerank-3-lite over the top 100 from a cheap first pass, at $0.02 per million tokens

## Connect

```bash
pip install voyageai   # or: npm i voyageai
```

```bash
curl https://api.voyageai.com/v1/embeddings \
  -H "Authorization: Bearer $VOYAGE_API_KEY" -H "content-type: application/json" \
  -d '{"model":"voyage-4","input":["What does the embeddings endpoint return?"],"input_type":"query","output_dimension":1024}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/voyage-ai

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Jina Embeddings and Reranker | C | 61.3 | embed.text, embed.multimodal, embed.code, embed.multilingual, rerank | https://www.anchorterminal.com/tools/jina-embeddings.min.md |
| Cohere Embed and Rerank | BB | 72.5 | embed.text, embed.multimodal, embed.multilingual, rerank | https://www.anchorterminal.com/tools/cohere-embed.min.md |
| Gemini Embedding | BB | 71 | embed.text, embed.multimodal, embed.code, embed.multilingual | https://www.anchorterminal.com/tools/gemini-embedding.min.md |
| ZeroEntropy zerank and zembed | F | 13.8 | rerank, embed.text, embed.multilingual | https://www.anchorterminal.com/tools/zeroentropy.min.md |
| OpenAI embeddings | BB | 73.4 | embed.text, embed.multilingual | https://www.anchorterminal.com/tools/openai-embeddings.min.md |


## Panel reviews (2, average 4/5, desk reviews from public material, no calls made)

- ★★★★☆ 200 million free tokens per model, and a card to opt out (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★★★☆ Four endpoints, clear model choice, and no OpenAPI file (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial)