Embeddings models
17 models in the catalog. Prices are the best (lowest) input price per million tokens across providers.
Embeddings models — best input prices
Embedding models map text to vectors for search, clustering and RAG pipelines. They are billed per 1M input tokens like every other model in the catalog; the table lists the lowest rate per provider.
| Model | Type | Providers | Input | Output | Last sync | |
|---|---|---|---|---|---|---|
AM
All MiniLM L6 v2
|
Embeddings | — | 1 | $0.009 | — | |
BM
Bge M3
|
Embeddings | — | 1 | $0.02 | — | |
| EL E5 Large V2 | Embeddings | — | 1 | $0.02 | — | |
| GL GTE Large EN v1.5 | Embeddings | — | 1 | $0.09 | — | |
| MQ Multi QA MPNet Base Dot v1 | Embeddings | — | 1 | $0.009 | — | |
QE
Qwen/Qwen3-Embedding-0.6B
|
Embeddings | — | 0 | — | — | |
|
QE
Qwen/Qwen3-Embedding-4B
|
Embeddings | — | 0 | — | — | |
|
QE
Qwen/Qwen3-Embedding-8B
|
Embeddings | — | 0 | — | — | |
|
QE
Qwen3 Embedding 0.6B
|
Embeddings | — | 1 | $0.04 | — | |
G3
google/embeddinggemma-300m
|
Embeddings | — | 0 | — | — | |
NQ
nvidia/embed-qa-4
|
Embeddings | — | 0 | — | — | |
|
N3
nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1
|
Embeddings | — | 0 | — | — | |
|
N3
nvidia/llama-3.2-nv-embedqa-1b-v1
|
Embeddings | — | 0 | — | — | |
|
NN
nvidia/llama-nemotron-embed-vl-1b-v2
|
Embeddings | — | 0 | — | — | |
|
N3
nvidia/nemotron-3-embed-1b
|
Embeddings | — | 0 | — | — | |
|
NE
nvidia/nv-embedqa-mistral-7b-v2
|
Embeddings | — | 0 | — | — | |
SE
snowflake/arctic-embed-l
|
Embeddings | — | 0 | — | — |