Nomic Embed v1.5
Open Weights
Nomic
Nomic's open text embedding model (February 2024), fully open with public weights, training code, and data. It offers an 8,192-token context - among the longest for open models - with Matryoshka dimensions, competitive quality, and reproducible, auditable training.
Strengths
- Fully open: weights, training code, and data
- 8,192-token context (among the longest for open models)
- Matryoshka dimensions for storage/latency trade-offs
- Competitive retrieval quality
- Reproducible, auditable training
Caveats
- Below the very top commercial models on some benchmarks
- Self-hosting requires embedding infrastructure
- English-strong; multilingual via the v2 line
- Vendor
- Nomic
- Context Window
- 8,192 tokens
- License
- Apache-2.0
- Release Date
- 2024-02-14
- Modalities
- text
Capabilities
Vision
Audio
Video
Tool Use
Resources
Pricing
Open weights under Apache 2.0 - free to self-host; also available via the Nomic Atlas API.