Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Voyage AI - API - verified

Voyage Context 3 embeddings

Voyage Context 3 is a legacy embedding model from Voyage AI, called by API as voyage-context-3. 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 $0.18 per 1M input tokens.

LegacyModel id: voyage-context-3

Default dims
1,024
Max input
32,000 tok
Price / 1M
$0.18
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
$0.18
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 Context 3. Call it with the model id voyage-context-3 as shown in the provider docs linked under Sources.

Worth knowing

Previous generation contextualized chunk embeddings with a 32,000-token per-chunk window and 120,000-token context length.

Release date not stated in the sources. Multilingual: yes.

FAQ

How many dimensions does Voyage Context 3 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 Context 3?

32,000 tokens per input, per Voyage AI's documentation. Longer text has to be chunked before you embed it.

How much does Voyage Context 3 cost?

The first-party list price is $0.18 per 1M input tokens. Older-model pricing with no free tokens. Source: https://docs.voyageai.com/docs/pricing.

What can Voyage Context 3 embed?

Text input, per the provider. It is documented as multilingual.

Should I still use Voyage Context 3?

Voyage AI lists Voyage Context 3 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.

More Voyage AI embedding models

Default dimensions, max input tokens and list price per 1M tokens.

All embedding models

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.