Voyage AI models & pricing

Voyage AI hosts 19 models (19 with public pricing) covering 2 modalities. voyage-3 family of state-of-the-art retrieval embeddings and rerankers. Cheapest input starts at $0.0200/M tokens; the most premium goes up to $0.180/M. Use Future AGI's Agent Command Center to route any Voyage AI model with cost-optimized fallback and unified observability.

Homepage ↗ Docs ↗

embedding 15

Model Input / 1M Output / 1M Context Caps
Voyage 3.5 Lite $0.0200/M 32,000
Voyage 3 Lite $0.0200/M 32,000
Voyage 3 $0.0600/M 32,000
Voyage 3.5 $0.0600/M 32,000
Voyage 2 $0.1000/M 4,000
Voyage Lite 01 $0.1000/M 4,096
Voyage Lite 02 Instruct $0.1000/M 4,000
Voyage Code 2 $0.120/M 16,000
Voyage Finance 2 $0.120/M 32,000
Voyage Large 2 $0.120/M 16,000
Voyage Law 2 $0.120/M 16,000
Voyage Multimodal 3 $0.120/M 32,000
Voyage 3 Large $0.180/M 32,000
Voyage Code 3 $0.180/M 32,000
Voyage Context 3 $0.180/M 120,000

rerank 4

Model Input / 1M Output / 1M Context Caps
Rerank 2.5 Lite $0.0200/M 32,000
Rerank 2 Lite $0.0200/M 8,000
Rerank 2 $0.0500/M 16,000
Rerank 2.5 $0.0500/M 32,000

FAQ

How many Voyage AI models are there?

19 Voyage AI models are listed across 2 modalities on this page. 19 have public per-token pricing.

How is Voyage AI pricing verified?

Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.

Which Voyage AI model is cheapest?

Input pricing on Voyage AI starts at $0.0200 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.

Can I route to Voyage AI via an OpenAI-compatible API?

Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Voyage AI target, and call Voyage AI models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.

Route any Voyage AI model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.