Wispr Flow - Don’t type, just speak
Mini tools| Model | Input | Cached input | Output | Unit |
|---|---|---|---|---|
|
rerank 2.5
This model
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
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 |
rerank 2.5
By Voyage AI
Model family: Rerank
rerank-2.5 is a reranking model designed to refine initial search results for improved retrieval accuracy. It introduces instruction-following capabilities, allowing users to steer relevance scores using natural language instructions alongside queries. These instructions can emphasize specific document sections, define document types, or disambiguate ambiguous queries. The model supports a 32K token context window, double that of its predecessor rerank-2 and 8x that of Cohere Rerank v3.5. It outperforms rerank-2 by 1.85% on standard retrieval benchmarks and by 7.94% over Cohere Rerank v3.5 across 93 datasets spanning 9 domains. On the MAIR benchmark for instruction-following retrieval, it surpasses Cohere Rerank v3.5 by 12.70%. Evaluated across 31 languages over 9 domains. Trained using improved mixture of training data and advanced distillation techniques from larger in-house instruction-following models. Priced identically to rerank-2 per token.
Text
Gen 7
Overview
A reranking model that reorders search results to improve retrieval accuracy, with instruction-following capabilities to steer relevance scoring via natural language. Supports 32K token context length. Outperforms previous models and competing rerankers across multiple domains and languages.
Pricing
Compare rerank 2.5 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
This model
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
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
