Embeddings
Models that turn text into vectors, for search and retrieval. Listed by input price, cheapest first. The first 25 of 27.
| Model | Input | Output | Context | Served by |
|---|---|---|---|---|
| google/embeddinggemma-300m | $0.002 per M | — | 2,048 tokens | deepinfra |
| BAAI/bge-base-en-v1.5 | $0.005 per M | — | 512 tokens | deepinfra |
| intfloat/e5-base-v2 | $0.005 per M | — | 512 tokens | deepinfra |
| sentence-transformers/all-MiniLM-L12-v2 | $0.005 per M | — | 512 tokens | deepinfra |
| sentence-transformers/all-MiniLM-L6-v2 | $0.005 per M | — | 512 tokens | deepinfra |
| sentence-transformers/all-mpnet-base-v2 | $0.005 per M | — | 512 tokens | deepinfra |
| sentence-transformers/clip-ViT-B-32 | $0.005 per M | — | 77 tokens | deepinfra |
| sentence-transformers/clip-ViT-B-32-multilingual-v1 | $0.005 per M | — | 512 tokens | deepinfra |
| sentence-transformers/multi-qa-mpnet-base-dot-v1 | $0.005 per M | — | 512 tokens | deepinfra |
| sentence-transformers/paraphrase-MiniLM-L6-v2 | $0.005 per M | — | 512 tokens | deepinfra |
| shibing624/text2vec-base-chinese | $0.005 per M | — | 512 tokens | deepinfra |
| thenlper/gte-base | $0.005 per M | — | 512 tokens | deepinfra |
| BAAI/bge-en-icl | $0.01 per M | — | 8,192 tokens | deepinfra |
| BAAI/bge-large-en-v1.5 | $0.01 per M | — | 512 tokens | deepinfra |
| BAAI/bge-m3 | $0.01 per M | — | 8,192 tokens | deepinfra |
| BAAI/bge-m3-multi | $0.01 per M | — | 512 tokens | deepinfra |
| BAAI/bge-m3-multi-8k | $0.01 per M | — | 8,192 tokens | deepinfra |
| Qwen/Qwen3-Embedding-0.6B | $0.01 per M | — | 32,768 tokens | deepinfra |
| Qwen/Qwen3-Embedding-8B | $0.01 per M | — | 32,768 tokens | deepinfra |
| intfloat/e5-large-v2 | $0.01 per M | — | 512 tokens | deepinfra |
| intfloat/multilingual-e5-large | $0.01 per M | — | 512 tokens | deepinfra |
| intfloat/multilingual-e5-large-instruct | $0.01 per M | — | 512 tokens | deepinfra |
| nvidia/llama-nemotron-embed-vl-1b-v2 | $0.01 per M | — | 10,240 tokens | deepinfra |
| thenlper/gte-large | $0.01 per M | — | 512 tokens | deepinfra |
| Qwen/Qwen3-Embedding-4B | $0.02 per M | — | 32,768 tokens | deepinfra |
Prices are the providers' list prices per million tokens, as of , on your own provider key with no fee on the tokens.