Embedding models for semantic search

For non-Latin text the tokenizer matters as much as the vector quality, so prefer a multilingual model and test it on your own documents. Embeddings are billed on input tokens only, which makes the one-off indexing pass cheap; the recurring cost sits in the answering step, not here.

40 models in this category · prices in toman per 1M tokens

Model	Capabilities	Context	Input / 1M	Output / 1M	≈ 1,000 words
LFM2.5-Embedding-350Mliquid/lfm-2.5-embedding-350m:free	Free · shared capacityEmbeddings	512	0	—	0.00
Llama Nemotron Embed VL 1B V2nvidia/llama-nemotron-embed-vl-1b-v2:free	Free · shared capacityImage inputEmbeddings	131,072	0	—	0.00
Nemotron 3 Embed 1Bnvidia/nemotron-3-embed-1b:free	Free · shared capacityEmbeddings	32,768	0	—	0.00
Nemotron 3.5 Embed 1Bnvidia/nemotron-3.5-embed-1b:free	Free · shared capacityImage inputEmbeddings	32,768	0	—	0.00
Nemotron 3.5 Embed 8Bnvidia/nemotron-3.5-embed-8b:free	Free · shared capacityImage inputEmbeddings	32,768	0	—	0.00
Embed V1 0.6Bperplexity/pplx-embed-v1-0.6b	Embeddings	32,000	1,385	—	1.80
bge-base-en-v1.5baai/bge-base-en-v1.5	Embeddings	512	1,731	—	2.25
E5-Base-v2intfloat/e5-base-v2	Embeddings	512	1,731	—	2.25
all-MiniLM-L12-v2sentence-transformers/all-minilm-l12-v2	Embeddings	512	1,731	—	2.25
all-MiniLM-L6-v2sentence-transformers/all-minilm-l6-v2	Embeddings	512	1,731	—	2.25
all-mpnet-base-v2sentence-transformers/all-mpnet-base-v2	Embeddings	512	1,731	—	2.25
multi-qa-mpnet-base-dot-v1sentence-transformers/multi-qa-mpnet-base-dot-v1	Embeddings	512	1,731	—	2.25
paraphrase-MiniLM-L6-v2sentence-transformers/paraphrase-minilm-l6-v2	Embeddings	512	1,731	—	2.25
GTE-Basethenlper/gte-base	Embeddings	512	1,731	—	2.25
bge-large-en-v1.5baai/bge-large-en-v1.5	Embeddings	512	3,462	—	4.50
bge-m3baai/bge-m3	Embeddings	8,194	3,462	—	4.50
E5-Large-v2intfloat/e5-large-v2	Embeddings	512	3,462	—	4.50
Multilingual-E5-Largeintfloat/multilingual-e5-large	Embeddings	512	3,462	—	4.50
Qwen3 Embedding 8Bqwen/qwen3-embedding-8b	Embeddings	40,960	3,462	—	4.50
GTE-Largethenlper/gte-large	Embeddings	512	3,462	—	4.50
Titan Text Embeddings V2amazon/titan-embed-text-v2	Embeddings	8,192	6,924	—	9.00
voyage-4-litemongodb/voyage-4-lite	Embeddings	32,000	6,924	—	9.00
Text Embedding 3 Smallopenai/text-embedding-3-small	Embeddings	8,192	6,924	—	9.00
Qwen3 Embedding 4Bqwen/qwen3-embedding-4b	Embeddings	32,768	6,924	—	9.00
Embed V1 4Bperplexity/pplx-embed-v1-4b	Embeddings	32,000	10,387	—	13.50
voyage-4mongodb/voyage-4	Embeddings	32,000	20,773	—	27.01
Embed 5 Fastcohere/embed-5-fast	Image inputEmbeddings	128,000	27,698	—	36.01
Titan Embeddings G1 - Textamazon/titan-embed-text-v1	Embeddings	8,192	34,622	—	45.01
Mistral Embed 2312mistralai/mistral-embed-2312	Embeddings	8,192	34,622	—	45.01
Text Embedding Ada 002openai/text-embedding-ada-002	Embeddings	8,192	34,622	—	45.01
Embed 5 Procohere/embed-5-pro	Image inputEmbeddings	128,000	41,546	—	54.01
voyage-4-largemongodb/voyage-4-large	Embeddings	32,000	41,546	—	54.01
voyage-code-4mongodb/voyage-code-4	Embeddings	32,000	41,546	—	54.01
voyage-multimodal-3.5mongodb/voyage-multimodal-3.5	Image inputEmbeddings	32,000	41,546	—	54.01
Text Embedding 3 Largeopenai/text-embedding-3-large	Embeddings	8,192	45,009	—	58.51
Gemini Embedding 001google/gemini-embedding-001	Embeddings	20,000	51,933	—	67.51
Codestral Embed 2505mistralai/codestral-embed-2505	Embeddings	8,192	51,933	—	67.51
Gemini Embedding 2google/gemini-embedding-2	Image inputFile inputAudio inputEmbeddings	8,192	69,244	—	90.02
Gemini Embedding 2 Previewgoogle/gemini-embedding-2-preview	Image inputFile inputAudio inputEmbeddings	8,192	69,244	—	90.02
Titan Multimodal Embeddings G1amazon/titan-embed-image-v1	Image inputEmbeddings	128	276,975	—	360.07