Wispr Flow - Don’t type, just speak
Mini tools| Model | Input | Cached input | Output | Unit |
|---|---|---|---|---|
|
rerank 2.5
Voyage AI
|
$0.05 | - | $0 | per 1M tokens |
|
Rerank 2.5 lite
Voyage AI
|
$0.02 | - | $0 | per 1M tokens |
|
Voyage 4
Voyage AI
|
$0.06 | - | $0 | per 1M tokens |
|
Voyage 4 large
Voyage AI
|
$0.12 | - | $0 | per 1M tokens |
|
Voyage 4 lite
This model
Voyage AI
|
$0.02 | - | $0 | per 1M tokens |
|
Voyage code 2
Voyage AI
|
$0.12 | - | $0 | per 1M tokens |
|
Voyage code 3
Voyage AI
|
$0.18 | - | $0 | per 1M tokens |
|
Voyage context 3
Voyage AI
|
$0.18 | - | $0 | per 1M tokens |
|
Voyage finance 2
Voyage AI
|
$0.12 | - | $0 | per 1M tokens |
|
Voyage law 2
Voyage AI
|
$0.12 | - | $0 | per 1M tokens |
|
Voyage multilingual 2
Voyage AI
|
$0.12 | - | $0 | per 1M tokens |
|
Voyage multimodal 3
Voyage AI
|
$0.12 | - | $0 | per 1M tokens |
|
Voyage multimodal 3.5
Voyage AI
|
$0.12 | - | $0 | per 1M tokens |
Voyage 4 lite
By Voyage AI
voyage-4-lite is a text embedding model in the Voyage 4 series, designed to approach the retrieval accuracy of voyage-3.5 while requiring significantly fewer parameters for reduced computational cost. It supports Matryoshka representation learning, enabling flexible embedding dimensions (2048, 1024, 512, or 256), and quantization-aware training for multiple output precision options: float (32-bit), int8, uint8, binary, and ubinary. The model supports a 32K token context window with optional input truncation. It shares an embedding space with voyage-4-large, voyage-4, and voyage-4-nano, enabling asymmetric retrieval where queries can be embedded with voyage-4-lite while documents are embedded with a larger model for better accuracy without re-vectorization. Available via the Voyage API, Azure AI Foundry, and MongoDB Atlas. Suited for semantic search, RAG pipelines, and high-volume retrieval use cases where latency and cost efficiency are priorities.
Text
Gen 7
Overview
Lightweight, general-purpose text embedding model optimized for low latency and cost. Supports a 32K token context window and flexible output dimensions (2048, 1024, 512, 256) via Matryoshka learning. Offers multiple quantization formats including float, int8, uint8, binary, and ubinary. Part of the Voyage 4 series with a shared embedding space across models.
Pricing
Compare Voyage 4 lite with other models listed in the same vendor pricing tiers and context lengths.
Tier
Standard
Batch
| Model | Input | Cached input | Output | Unit |
|---|---|---|---|---|
|
rerank 2.5
Voyage AI
|
$0.0335 | - | $0 | per 1M tokens |
|
Rerank 2.5 lite
Voyage AI
|
$0.0134 | - | $0 | per 1M tokens |
|
Voyage 4
Voyage AI
|
$0.0402 | - | $0 | per 1M tokens |
|
Voyage 4 large
Voyage AI
|
$0.0804 | - | $0 | per 1M tokens |
|
Voyage 4 lite
This model
Voyage AI
|
$0.0134 | - | $0 | per 1M tokens |
|
Voyage code 2
Voyage AI
|
$0.0804 | - | $0 | per 1M tokens |
|
Voyage code 3
Voyage AI
|
$0.1206 | - | $0 | per 1M tokens |
|
Voyage context 3
Voyage AI
|
$0.1206 | - | $0 | per 1M tokens |
|
Voyage finance 2
Voyage AI
|
$0.0804 | - | $0 | per 1M tokens |
|
Voyage law 2
Voyage AI
|
$0.0804 | - | $0 | per 1M tokens |
|
Voyage multilingual 2
Voyage AI
|
$0.0804 | - | $0 | per 1M tokens |
|
Voyage multimodal 3
Voyage AI
|
$0.0804 | - | $0 | per 1M tokens |
|
Voyage multimodal 3.5
Voyage AI
|
$0.0804 | - | $0 | per 1M tokens |
About Voyage AI
Voyage AI provides best-in-class embedding models and rerankers for search and retrieval over unstructured data, used to power retrieval-augmented generation (RAG) and AI applications. It offers general-purpose, domain-specific (finance, legal, code) and company-specific fine-tuned models. Founded in 2023 and based in Palo Alto, the company was acquired by MongoDB, Inc. in February 2025 and now operates as a MongoDB subsidiary.
View Company Profile
Last updated: June 24, 2026
