Voyage: Voyage 4 Lite

Voyage 4 Lite focuses on latency and cost within Voyage's fourth-generation retrieval family. Its embeddings are compatible with Voyage 4 and Voyage 4 Large, which is useful when a search application embeds frequent queries against an existing family index.

Compare models

voyage-4-lite

AvailableVoyageEmbeddingSync

Input / Output: $0.02 / $0.00
Context: 32K
Modalities: Embedding

About Voyage 4 Lite

Voyage 4 Lite is the latency- and cost-oriented text embedding model in Voyage AI's fourth series. Its vectors are compatible with Voyage 4 and Voyage 4 Large, which makes it a natural choice for embedding high-volume user queries against an index built by a larger family member. It returns 1024 dimensions by default and also supports 256, 512, and 2048.

Where it works well

Voyage optimizes it for latency and cost within Series 4.
Query vectors from it match document vectors produced by Voyage 4 or Voyage 4 Large.
The same four dimension options as the larger models are available.
It succeeds Voyage 3.5 Lite as the recommended upgrade.

When to choose another model

Retrieval quality sits below Voyage 4 and Voyage 4 Large, so a quality-critical index is better built with those.
It embeds text only and is not specialised for code, finance, or legal text.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

EmbeddingTokenLab endpoint

POST/v1/embeddings

curl -X POST "https://api.tokenlab.sh/v1/embeddings" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "encoding_format": "float",
  "model": "voyage-4-lite",
  "input": "The quick brown fox jumps over the lazy dog."
}'

Parameters

Embedding

Parameter	Values and limits	Default	Notes
`encoding_format`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`input`	Inputs: ≥ 1, ≤ 1000	Not provided	Not provided

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Embedding

per 1M tokens

Official price: Input $0.02 / Output $0.00
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Embedding	Input $0.02 / Output $0.00	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 15, 2026, 1:51 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Voyage 4 Lite in Console with a prompt ready to edit or send.

Help me try voyage-4-lite with embedding at /v1/embeddings. Show the result and cost.

Use cases

Live query embedding
Embed every search request with the light model while documents stay indexed by a larger family member.
Large-scale chatbot memory
Embed many short messages to retrieve earlier conversation turns without heavy embedding workloads.
Budget prototypes
Stand up a retrieval prototype quickly, then raise the model tier only if evaluation shows a gap.

Prompt examples

Embed the query: refund policy for annual plans.

Embed this chat message for the conversation memory store.

Embed the query in Spanish: cómo cambiar mi contraseña.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is Voyage 4 Lite best at?

Fast, inexpensive embedding. Voyage describes it as optimized for latency and cost. It suits frequent, short inputs such as search queries, where per-request speed counts more than the last bit of retrieval quality.

Can Voyage 4 Lite search an index made with Voyage 4 Large?

Yes. Voyage states that Series 4 embeddings are compatible, so Lite query vectors can be compared with documents embedded by Large. Test recall on your own queries to confirm the quality trade-off is acceptable.

How does Voyage 4 Lite differ from Voyage 3.5 Lite?

Voyage 4 Lite is the current-generation model, and Voyage points to it as the upgrade from Voyage 3.5 Lite. The generations use different vector spaces, so moving over requires re-embedding your stored documents.

What dimensions does it return?

The default is 1024, with 256, 512, and 2048 available. Smaller values reduce storage and search time. Keep one value across the whole index so documents and queries stay comparable.

How much does Voyage 4 Lite cost?

On TokenLab, Voyage 4 Lite costs Input $0.02 / Output $0.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Voyage 4 Lite use?

Use https://api.tokenlab.sh/v1/embeddings for Voyage 4 Lite. The request example below shows the matching code shape.

Which operations does Voyage 4 Lite support?

Voyage 4 Lite supports Embedding. Select an operation above to see its endpoint and request example.