|
The Voyage 4 model family: shared embedding space with MoE architecture
|
Voyage AI |
2026-01-15 |
973 |
--
|
|
Stronger Together: Why We Chose to Join MongoDB
|
Voyage AI |
2025-02-24 |
550 |
--
|
|
The Case Against LLMs as Rerankers
|
Voyage AI |
2025-10-22 |
2,130 |
--
|
|
Accelerating our mission: building the best embedding models for all developers
|
Voyage AI |
2025-05-06 |
398 |
--
|
|
Introducing voyage-context-3: focused chunk-level details with global document context
|
Voyage AI |
2025-07-23 |
1,724 |
--
|
|
voyage-3-large: the new state-of-the-art general-purpose embedding model
|
Voyage AI |
2025-01-07 |
838 |
--
|
|
voyage-multimodal-3.5: a new multimodal retrieval frontier with video support
|
Voyage AI |
2026-01-15 |
1,089 |
--
|
|
Introducing the Batch API: Simpler and more efficient for large-scale workloads
|
Voyage AI |
2025-12-04 |
428 |
--
|
|
rerank-2.5 and rerank-2.5-lite: instruction-following rerankers
|
Voyage AI |
2025-08-11 |
1,701 |
--
|
|
Announcing New Models and Expanded Availability
|
Voyage AI |
2026-01-15 |
372 |
--
|
|
voyage-3.5 and voyage-3.5-lite: improved quality for a new retrieval frontier
|
Voyage AI |
2025-05-20 |
758 |
--
|
|
Breaking the Dense Ceiling: How voyage-4-large Uses MoE to Scale
|
Voyage AI |
2026-03-03 |
1,207 |
--
|
|
voyage-context-4: stop worrying about chunking with our best-performing model
|
Voyage AI |
2026-06-30 |
1,223 |
--
|
