Embedding models
27 embedding models that turn text into vectors for search, RAG and clustering, priced per 1M input tokens.
| BGE M3BAAIMIT | $0.01/1Mvia APIYI | — | — | 17K | Jan 27, 2024 | |
 Qwen 3 Embedding 4BAlibabaApache 2.0 | $0.019/1Mvia SiliconFlow | 33K | 4B | 5K | Jun 3, 2025 | |
 Nemotron 3.5 Embed 1BNVIDIAOpen weights · permissive | Free/1Mvia Nvidia | — | 1.6B | 4K | Oct 7 | |
| Qwen3 Embedding 0.6BAlibabaApache 2.0 | $0.01/1Mvia SiliconFlow | 33K | 596M | 2K | Jun 3, 2025 | |
| Nemotron 3 Embed 1BNVIDIAOpen weights · permissive | Free/1Mvia Nvidia | — | 1.1B | 390 | Jul 14 | |
| Bge Large En V1.5BAAIMITJSON+2 | $0.034/1Mvia AIHubMix | — | 335M | — | Sep 12, 2023 | |
| Bge Large Zh V1.5BAAIMITJSON+2 | $0.034/1Mvia AIHubMix | — | — | — | Sep 12, 2023 | |
 Doubao Embedding Large TextByteDance | $0.10/1Mvia AIHubMix | — | — | — | — | |
| Doubao Embedding TextByteDance | $0.70/1Mvia AIHubMix | — | — | — | — | |
| Embed Qa 4NVIDIA | Free/1Mvia Nvidia | — | — | — | — | |
 Gemini EmbeddingGoogle | $0.02/1Mvia AIHubMix | — | — | — | — | |
| Gemini Embedding 001Google | $0.15/1Mvia AIHubMix | 2K | — | — | May 20, 2025 | |
| Gemini Embedding 2GoogleVision | $0.20/1Mvia APIYI | 8K | — | — | Mar 10 | |
| Gemini Embedding 2 PreviewGoogleVision | $0.20/1Mvia OrcaRouter | — | — | — | — | |
| Llama 3.2 Nemoretriever 1B Vlm Embed V1NVIDIA | Free/1Mvia Nvidia | — | 1B | — | — | |
| Llama 3.2 Nv Embedqa 1B V1NVIDIA | Free/1Mvia Nvidia | — | 1B | — | — | |
| Llama Nemotron Embed VL 1B V2NVIDIAOpen weights · with terms | Free/1Mvia Nvidia | — | 1.7B | — | Dec 3, 2025 | |
| Nemotron 3.5 Embed 8BNVIDIAOpen weights · permissive | Free/1Mvia Nvidia | — | 8.4B | — | Oct 7 | |
| Nv Embedqa Mistral 7B V2NVIDIA | Free/1Mvia Nvidia | — | 7B | — | — | |
| NvclipNVIDIA | Free/1Mvia Nvidia | — | — | — | — | |
| Qwen3 Embedding 8BAlibabaApache 2.0 | $0.039/1Mvia SiliconFlow | 33K | 7.6B | — | Jun 3, 2025 | |
| Qwen3-VL Embedding 8BAlibabaApache 2.0Vision | $0.097/1Mvia SiliconFlow | 8K | 8.1B | — | Jan 7 | |
| Text Embedding 005Google | Free/1Mvia DevPass (LLM Gateway) | — | — | — | Aug 1, 2024 | |
| Text Embedding 3 LargeOpenAI | $0.104/1Mvia APIMart | 8K | — | — | Jan 25, 2024 | |
| Text Embedding 3 SmallOpenAI | $0.016/1Mvia APIMart | 8K | — | — | Jan 25, 2024 | |
| Text Embedding Ada 002OpenAI | $0.08/1Mvia APIMart | 8K | — | — | Dec 15, 2022 | |
| Text Multilingual Embedding 002Google | Free/1Mvia DevPass (LLM Gateway) | — | — | — | Mar 1, 2024 |
Frequently asked questions
A model that turns text into a list of numbers (a vector) so that similar meanings land close together. Search, retrieval-augmented generation (RAG), recommendations and deduplication are built on them.
Embeddings are among the cheapest AI calls: most cost a few cents per million input tokens, and some open models are hosted for free. The list shows the lowest price for each model and who sells it.
Open models such as BGE and Qwen3 Embedding can run on your own hardware, so the data never leaves it and there is no per-token bill. Hosted APIs are simpler to start with; dimensions and context length matter more than the brand.
Can't find what you're looking for? Contact us