Voyage AI - API - verified
Voyage 3.5 Lite embeddings
Voyage 3.5 Lite is a legacy embedding model from Voyage AI, called by API as voyage-3.5-lite. It returns 1,024-dimension vectors by default and accepts up to 32,000 input tokens, for text input. The first-party list price is $0.02 per 1M input tokens.
LegacyModel id: voyage-3.5-lite
- Default dims
- 1,024
- Max input
- 32,000 tok
- Price / 1M
- $0.02
- Inputs
- Text
Dimensions
Flexible output size- 2,048
- 1,024default
- 512
- 256
Default output: 1,024 dimensions.
Listed sizes: 2,048, 1,024, 512 and 256.
Voyage AI documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.
Pricing
- Per 1M input tokens
- $0.02
- Batch, per 1M
- Not stated
Older-model pricing with no free tokens.
Source: docs.voyageai.com/docs/pricing
Usage
The sources read for this directory publish no copyable snippet for Voyage 3.5 Lite. Call it with the model id voyage-3.5-lite as shown in the provider docs linked under Sources.
Worth knowing
Listed under older models still accessible from the API; Voyage recommends the 4 series.
Release date not stated in the sources. Multilingual: not stated.
FAQ
How many dimensions does Voyage 3.5 Lite output?
Default output: 1,024 dimensions. Listed sizes: 2,048, 1,024, 512 and 256. Voyage AI documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.
What is the max input length of Voyage 3.5 Lite?
32,000 tokens per input, per Voyage AI's documentation. Longer text has to be chunked before you embed it.
How much does Voyage 3.5 Lite cost?
The first-party list price is $0.02 per 1M input tokens. Older-model pricing with no free tokens. Source: https://docs.voyageai.com/docs/pricing.
What can Voyage 3.5 Lite embed?
Text input, per the provider.
Should I still use Voyage 3.5 Lite?
Voyage AI lists Voyage 3.5 Lite as an older model. Existing indexes keep working while it is served, but vectors from different models cannot be mixed, so moving to a newer model means re-embedding your corpus.
Sources
Last verified from the pages below.
- Voyage text embeddings docs - docs.voyageai.com
- Voyage pricing - docs.voyageai.com
More Voyage AI embedding models
Default dimensions, max input tokens and list price per 1M tokens.
- Voyage 4 Large1,024 dims - 32,000 tokens - $0.12
- Voyage 41,024 dims - 32,000 tokens - $0.06
- Voyage 4 Lite1,024 dims - 32,000 tokens - $0.02
- Voyage Code 41,024 dims - 32,000 tokens - $0.12
- Voyage Context 41,024 dims - 32,000 tokens - $0.12
- Voyage Multimodal 3.51,024 dims - 32,000 tokens - $0.12
- Voyage Finance 21,024 dims - 32,000 tokens - $0.12
- Voyage Law 21,024 dims - 16,000 tokens - $0.12
- Voyage 4 Nano1,024 dims - 32,000 tokens - Self-hosted
- Voyage 3 LargeLegacy1,024 dims - 32,000 tokens - $0.18
- Voyage 3.5Legacy1,024 dims - 32,000 tokens - $0.06
- Voyage Code 3Legacy1,024 dims - 32,000 tokens - $0.18
- Voyage Context 3Legacy1,024 dims - 32,000 tokens - $0.18
- Voyage Multimodal 3Legacy1,024 dims - 32,000 tokens - $0.12
- Voyage 3Legacy1,024 dims - 32,000 tokens - $0.06
- Voyage 3 LiteLegacy512 dims - 32,000 tokens - $0.02
- Voyage Multilingual 2Legacy1,024 dims - 32,000 tokens - $0.12
- Voyage Large 2 InstructLegacy1,024 dims - 16,000 tokens - $0.12
- Voyage Large 2Legacy1,536 dims - 16,000 tokens - $0.12
- Voyage 2Legacy1,024 dims - 4,000 tokens - $0.10
Newsletter
New models, every week
One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.
Keep exploring
Model API pricing and specs
First-party prices per 1M tokens for chat and reasoning models.
Local models
Open-weight LLMs you can download and run, with sizes and licenses.
What is RAG?
Where embeddings fit in a retrieval pipeline, end to end.
Vector databases compared
Where the vectors go once you have picked a model.