Liquid AI's open-weight decision model, giving yes or no, choice or score answers from text and images
TrustList summary
The documentation for Voyage's text embeddings files voyage-3 under older models, not among the current ones. It is a general-purpose embedding model tuned for multilingual retrieval quality, with a 32,000 token context and 1,024-dimension vectors.
A previous-generation model
The page's main table now leads with the 4 series: voyage-4-large, voyage-4 and voyage-4-lite, plus specialised models for code, finance and law. It says the older models remain accessible through the API but recommends the newer ones for better quality and efficiency, and that the latest models will be strictly better than the legacy ones in quality, context length, latency and throughput. voyage-3 therefore stays available while Voyage points new work to the 4 series.
Its neighbours in the same era
Other previous-generation entries include voyage-3-large, voyage-3.5 and voyage-3.5-lite, voyage-3-lite (512 dimensions, aimed at latency and cost), voyage-code-3 and voyage-multilingual-2. Several earlier models, some marked deprecated, carry advice to transition to voyage-3, which is why this name appears so often in the documentation.
Using it from Python
Voyage text embeddings are reached through the voyageai Python package. After installing it and setting an API key, a call to the client's embed function takes a list of texts, a model name and optional settings: input type, truncation, output dimension and output data type. A list may hold at most 1,000 texts, and the documentation sets separate token totals per model. The surrounding guides cover rerankers, multimodal and contextualized chunk embeddings, flexible dimensions and quantization, batch inference, rate limits and deployment inside a customer's VPC through AWS and Azure marketplaces.
Summary written by TrustList from the business's own published information, Nov 2026.
Benchmarks & AI stats
| Benchmark | Official | Community avg |
|---|---|---|
| No benchmark scores yet. Be the first to add one. | ||
“Official” values are editor-approved and feed the ranking. “Community avg” is the mean of member submissions (shown for transparency; it never affects the ranking until an editor approves a value).
Sign in to add a benchmark score for this model.
voyage-3 launches
Request a demo or quote from voyage-3
Reviews
Questions & answers
No questions yet. Be the first to ask about voyage-3.
voyage-3 alternatives
Similar listings buyers compare against this one.
Open-weight translation model from Bilibili's Index team, covering 150 languages and following glossary and style instructions
Open-source 2B decision model from AWS's Strands Agents project that picks options and returns scores with a reliability figure
Microsoft AI's real-time speech-to-text model for voice agents, transcribing 60 languages with continuous language detection
Google's open multimodal embedding model that maps text, images, audio and video into one vector space, under Apache 2.0
Perplexity's open-weight decision model that picks among given options for routing and checks in AI systems
Cantina Security's first open-weight security model, a post-trained GLM-5.3-Flash for vulnerability research and exploit checks
Microsoft AI's text-to-speech model for keeping one voice across 23 languages, with voice cloning from short audio
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.