Fully Informed Run a panel →

Embedding models

Models that turn text into vector embeddings for semantic search, RAG and clustering. 27 models available.

← All models

Baai

BAAI: bge-base-en-v1.5$0.01 / 1M tokensBAAI: bge-large-en-v1.5$0.01 / 1M tokensBAAI: bge-m3$0.01 / 1M tokens

Google

Google: Gemini Embedding 001$0.15 / 1M tokensGoogle: Gemini Embedding 2$0.20 / 1M tokensGoogle: Gemini Embedding 2 Preview$0.20 / 1M tokens

Intfloat

Intfloat: E5-Base-v2$0.01 / 1M tokensIntfloat: E5-Large-v2$0.01 / 1M tokensIntfloat: Multilingual-E5-Large$0.01 / 1M tokens

Mistralai

Mistral: Codestral Embed 2505$0.15 / 1M tokensMistral: Mistral Embed 2312$0.10 / 1M tokens

Nvidia

NVIDIA: Llama Nemotron Embed VL 1B V2 (free)FreeNVIDIA: Nemotron 3 Embed 1B (free)Free

Openai

OpenAI: Text Embedding 3 Large$0.13 / 1M tokensOpenAI: Text Embedding 3 Small$0.02 / 1M tokensOpenAI: Text Embedding Ada 002$0.10 / 1M tokens

Perplexity

Perplexity: Embed V1 0.6B$0.00 / 1M tokensPerplexity: Embed V1 4B$0.03 / 1M tokens

Qwen

Qwen: Qwen3 Embedding 4B$0.02 / 1M tokensQwen: Qwen3 Embedding 8B$0.01 / 1M tokens

Sentence-transformers

Sentence Transformers: all-MiniLM-L12-v2$0.01 / 1M tokensSentence Transformers: all-MiniLM-L6-v2$0.01 / 1M tokensSentence Transformers: all-mpnet-base-v2$0.01 / 1M tokensSentence Transformers: multi-qa-mpnet-base-dot-v1$0.01 / 1M tokensSentence Transformers: paraphrase-MiniLM-L6-v2$0.01 / 1M tokens

Thenlper

Thenlper: GTE-Base$0.01 / 1M tokensThenlper: GTE-Large$0.01 / 1M tokens
← All models